Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.7235. Min Act: -0.1700
Data Index: 2000499 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.6453. Min Act: -0.1700
Data Index: 2290054 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.5514. Min Act: -0.1700
Data Index: 1091519 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.5357. Min Act: -0.1700
Data Index: 3646981 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.5044. Min Act: -0.1700
Data Index: 947618 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4731. Min Act: -0.1700
Data Index: 5919260 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4417. Min Act: -0.1700
Data Index: 270723 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4574. Min Act: -0.1700
Data Index: 3609288 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4574. Min Act: -0.1700
Data Index: 8067664 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4261. Min Act: -0.1700
Data Index: 5548313 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4417. Min Act: -0.1700
Data Index: 58894 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4261. Min Act: -0.1700
Data Index: 4138395 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4417. Min Act: -0.1700
Data Index: 1455949 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4261. Min Act: -0.1700
Data Index: 955037 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4261. Min Act: -0.1700
Data Index: 4592244 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4417. Min Act: -0.1700
Data Index: 6792877 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4261. Min Act: -0.1700
Data Index: 5053028 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4104. Min Act: -0.1700
Data Index: 3191185 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.4104. Min Act: -0.1700
Data Index: 5963805 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7235. Min Range: -3.7235
Max Act: 3.3947. Min Act: -0.1700
Data Index: 4973941 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19