Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 370 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1960. Min Range: -4.1960
Max Act: 4.1960. Min Act: -0.1700
Data Index: 4215050 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1960. Min Range: -4.1960
Max Act: 4.1335. Min Act: -0.1700
Data Index: 4215047 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1960. Min Range: -4.1960
Max Act: 4.0710. Min Act: -0.1700
Data Index: 2399856 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1960. Min Range: -4.1960
Max Act: 4.0085. Min Act: -0.1700
Data Index: 2012989 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1960. Min Range: -4.1960
Max Act: 4.0085. Min Act: -0.1700
Data Index: 5604889 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1960. Min Range: -4.1960
Max Act: 4.0085. Min Act: -0.1700
Data Index: 3544589 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9772. Min Act: -0.1700
Data Index: 895819 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9459. Min Act: -0.1700
Data Index: 847720 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9459. Min Act: -0.1700
Data Index: 2012987 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9459. Min Act: -0.1700
Data Index: 6481723 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9459. Min Act: -0.1700
Data Index: 2012986 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9459. Min Act: -0.1700
Data Index: 8066616 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9459. Min Act: -0.1700
Data Index: 693118 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9147. Min Act: -0.1700
Data Index: 4215048 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9147. Min Act: -0.1700
Data Index: 1503148 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9147. Min Act: -0.1700
Data Index: 4215051 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9147. Min Act: -0.1700
Data Index: 1537259 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9147. Min Act: -0.1700
Data Index: 6735306 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9147. Min Act: -0.1700
Data Index: 6545682 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1960. Min Range: -4.1960
Max Act: 3.9459. Min Act: -0.1700
Data Index: 5604891 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19