Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1659 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4601. Min Range: -6.4601
Max Act: 6.4601. Min Act: -0.1700
Data Index: 5219455 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4601. Min Range: -6.4601
Max Act: 6.1163. Min Act: -0.1700
Data Index: 1953758 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.8351. Min Act: -0.1700
Data Index: 2649202 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.8038. Min Act: -0.1700
Data Index: 85489 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.7726. Min Act: -0.1700
Data Index: 5219454 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.7413. Min Act: -0.1700
Data Index: 3357627 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.7101. Min Act: -0.1700
Data Index: 1504868 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.7101. Min Act: -0.1700
Data Index: 7287942 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.6788. Min Act: -0.1700
Data Index: 8353351 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.6476. Min Act: -0.1700
Data Index: 5144873 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.6163. Min Act: -0.1700
Data Index: 6011094 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.6476. Min Act: -0.1700
Data Index: 6916599 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.6163. Min Act: -0.1700
Data Index: 3357628 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.6163. Min Act: -0.1700
Data Index: 6962229 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.6163. Min Act: -0.1700
Data Index: 7054125 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.6476. Min Act: -0.1700
Data Index: 8353350 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.5851. Min Act: -0.1700
Data Index: 3551394 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.5538. Min Act: -0.1700
Data Index: 6926289 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.4913. Min Act: -0.1700
Data Index: 4266422 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4601. Min Range: -6.4601
Max Act: 5.4913. Min Act: -0.1700
Data Index: 27698 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19