Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2038. Min Range: -12.2038
Max Act: 12.2038. Min Act: -0.1700
Data Index: 1168246 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.6413. Min Act: -0.1700
Data Index: 3947012 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.5163. Min Act: -0.1700
Data Index: 6311912 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.5163. Min Act: -0.1700
Data Index: 8388006 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.3913. Min Act: -0.1700
Data Index: 5437214 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.4538. Min Act: -0.1700
Data Index: 1514015 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.3288. Min Act: -0.1700
Data Index: 5446037 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.3288. Min Act: -0.1700
Data Index: 1569875 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.3288. Min Act: -0.1700
Data Index: 3826598 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.2038. Min Act: -0.1700
Data Index: 4411742 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.2663. Min Act: -0.1700
Data Index: 8125262 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.2663. Min Act: -0.1700
Data Index: 7963236 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.2038. Min Act: -0.1700
Data Index: 3038730 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.2663. Min Act: -0.1700
Data Index: 2784006 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.2038. Min Act: -0.1700
Data Index: 3816490 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.2663. Min Act: -0.1700
Data Index: 3112284 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.2038. Min Act: -0.1700
Data Index: 217610 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.1413. Min Act: -0.1700
Data Index: 4485889 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.1413. Min Act: -0.1700
Data Index: 2254556 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2038. Min Range: -12.2038
Max Act: 11.1413. Min Act: -0.1700
Data Index: 8110242 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19