Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4646 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.4960. Min Act: -0.1700
Data Index: 8307291 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.4177. Min Act: -0.1700
Data Index: 1766413 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.4333. Min Act: -0.1700
Data Index: 6347895 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.4020. Min Act: -0.1700
Data Index: 5524970 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.3706. Min Act: -0.1700
Data Index: 584855 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.3549. Min Act: -0.1700
Data Index: 7223157 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.3392. Min Act: -0.1700
Data Index: 5025255 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.3392. Min Act: -0.1700
Data Index: 2829944 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.3236. Min Act: -0.1700
Data Index: 746722 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.3079. Min Act: -0.1700
Data Index: 505875 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.3236. Min Act: -0.1700
Data Index: 6226838 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.2922. Min Act: -0.1700
Data Index: 5525085 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.3079. Min Act: -0.1700
Data Index: 6293559 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.2765. Min Act: -0.1700
Data Index: 335006 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.2765. Min Act: -0.1700
Data Index: 4435262 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.2765. Min Act: -0.1700
Data Index: 5031186 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.2765. Min Act: -0.1700
Data Index: 690316 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.2608. Min Act: -0.1700
Data Index: 500651 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.2765. Min Act: -0.1700
Data Index: 554620 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4960. Min Range: -3.4960
Max Act: 3.2450. Min Act: -0.1700
Data Index: 3188267 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19