Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 957 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.7026. Min Act: -0.1700
Data Index: 1185179 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.6087. Min Act: -0.1700
Data Index: 5737848 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.5461. Min Act: -0.1700
Data Index: 594270 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.5148. Min Act: -0.1700
Data Index: 1778764 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.4835. Min Act: -0.1700
Data Index: 2521369 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.4678. Min Act: -0.1700
Data Index: 6111002 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.4678. Min Act: -0.1700
Data Index: 4692223 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.4365. Min Act: -0.1700
Data Index: 3174482 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.4365. Min Act: -0.1700
Data Index: 6655243 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.4051. Min Act: -0.1700
Data Index: 4942127 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.4051. Min Act: -0.1700
Data Index: 4641741 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.3894. Min Act: -0.1700
Data Index: 2624580 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.3737. Min Act: -0.1700
Data Index: 8452140 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.4051. Min Act: -0.1700
Data Index: 408777 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.3894. Min Act: -0.1700
Data Index: 4326688 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.3737. Min Act: -0.1700
Data Index: 3970276 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.3737. Min Act: -0.1700
Data Index: 8772815 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.3737. Min Act: -0.1700
Data Index: 1791976 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.4051. Min Act: -0.1700
Data Index: 8787363 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7026. Min Range: -3.7026
Max Act: 3.3894. Min Act: -0.1700
Data Index: 3745264 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19