Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2157 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0128. Min Range: -4.0128
Max Act: 4.0128. Min Act: -0.1700
Data Index: 3364955 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9815. Min Act: -0.1700
Data Index: 190964 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.9502. Min Act: -0.1700
Data Index: 7888016 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.8564. Min Act: -0.1700
Data Index: 6760417 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.8564. Min Act: -0.1700
Data Index: 1715090 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.8564. Min Act: -0.1700
Data Index: 8722984 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.8252. Min Act: -0.1700
Data Index: 1202254 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.8252. Min Act: -0.1700
Data Index: 4452078 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7939. Min Act: -0.1700
Data Index: 2893384 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7939. Min Act: -0.1700
Data Index: 8116230 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7939. Min Act: -0.1700
Data Index: 3014626 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7626. Min Act: -0.1700
Data Index: 8348929 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7626. Min Act: -0.1700
Data Index: 1477889 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7626. Min Act: -0.1700
Data Index: 5366722 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7626. Min Act: -0.1700
Data Index: 8800704 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7626. Min Act: -0.1700
Data Index: 4138864 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7313. Min Act: -0.1700
Data Index: 885518 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7313. Min Act: -0.1700
Data Index: 7172407 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7313. Min Act: -0.1700
Data Index: 7203314 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0128. Min Range: -4.0128
Max Act: 3.7313. Min Act: -0.1700
Data Index: 7293576 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19