Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2037. Min Range: -4.2037
Max Act: 4.2037. Min Act: -0.1700
Data Index: 1026008 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2037. Min Range: -4.2037
Max Act: 4.1412. Min Act: -0.1700
Data Index: 4307839 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2037. Min Range: -4.2037
Max Act: 4.0787. Min Act: -0.1700
Data Index: 7775219 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.9849. Min Act: -0.1700
Data Index: 2110794 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.9537. Min Act: -0.1700
Data Index: 5481838 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.9537. Min Act: -0.1700
Data Index: 5390033 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.8912. Min Act: -0.1700
Data Index: 4689979 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.8912. Min Act: -0.1700
Data Index: 4948910 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.8286. Min Act: -0.1700
Data Index: 2752718 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.8286. Min Act: -0.1700
Data Index: 1255655 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.8286. Min Act: -0.1700
Data Index: 1630214 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.7661. Min Act: -0.1700
Data Index: 2972055 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.7661. Min Act: -0.1700
Data Index: 5535101 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.7661. Min Act: -0.1700
Data Index: 6491402 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.7504. Min Act: -0.1700
Data Index: 7777681 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.7504. Min Act: -0.1700
Data Index: 3848483 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.7348. Min Act: -0.1700
Data Index: 5658351 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.7348. Min Act: -0.1700
Data Index: 5272932 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.7191. Min Act: -0.1700
Data Index: 6763991 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2037. Min Range: -4.2037
Max Act: 3.7191. Min Act: -0.1700
Data Index: 58674 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19