Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.4374. Min Act: -0.1700
Data Index: 102375 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.3749. Min Act: -0.1700
Data Index: 2728058 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.3124. Min Act: -0.1700
Data Index: 5805146 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.3124. Min Act: -0.1700
Data Index: 7824489 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.3124. Min Act: -0.1700
Data Index: 3914455 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.3124. Min Act: -0.1700
Data Index: 325621 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.2811. Min Act: -0.1700
Data Index: 3887839 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.2499. Min Act: -0.1700
Data Index: 7202328 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.2186. Min Act: -0.1700
Data Index: 2005977 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.2186. Min Act: -0.1700
Data Index: 2715743 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.2186. Min Act: -0.1700
Data Index: 4016897 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.2186. Min Act: -0.1700
Data Index: 6262706 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.1874. Min Act: -0.1700
Data Index: 5633157 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.1874. Min Act: -0.1700
Data Index: 6477570 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.1874. Min Act: -0.1700
Data Index: 8365424 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.1874. Min Act: -0.1700
Data Index: 2845037 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.1874. Min Act: -0.1700
Data Index: 2161927 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.1874. Min Act: -0.1700
Data Index: 2086145 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.1561. Min Act: -0.1700
Data Index: 6578267 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4374. Min Range: -6.4374
Max Act: 6.1561. Min Act: -0.1700
Data Index: 4975507 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19