Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1436 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.9947. Min Act: -0.1700
Data Index: 3296183 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.7727. Min Act: -0.1700
Data Index: 6358837 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.8243. Min Act: -0.1700
Data Index: 8616461 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.7554. Min Act: -0.1700
Data Index: 4465305 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.7554. Min Act: -0.1700
Data Index: 8673137 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.7640. Min Act: -0.1700
Data Index: 3243098 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.6862. Min Act: -0.1700
Data Index: 203935 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.6948. Min Act: -0.1700
Data Index: 3316625 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.7122. Min Act: -0.1700
Data Index: 1535368 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.7208. Min Act: -0.1700
Data Index: 1621767 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.7208. Min Act: -0.1700
Data Index: 1097552 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.6862. Min Act: -0.1700
Data Index: 2536710 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.6775. Min Act: -0.1700
Data Index: 4600994 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.6427. Min Act: -0.1700
Data Index: 1598096 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.6340. Min Act: -0.1700
Data Index: 5633568 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.6165. Min Act: -0.1700
Data Index: 3656708 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.6601. Min Act: -0.1700
Data Index: 1246394 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.6078. Min Act: -0.1700
Data Index: 7973769 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.6514. Min Act: -0.1700
Data Index: 1582422 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9947. Min Range: -1.9947
Max Act: 1.6253. Min Act: -0.1700
Data Index: 6267131 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19