Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5115 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.4233. Min Act: -0.1700
Data Index: 3770071 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3608. Min Act: -0.1700
Data Index: 2276587 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3296. Min Act: -0.1697
Data Index: 3309100 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3296. Min Act: -0.1700
Data Index: 4536431 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2983. Min Act: -0.1700
Data Index: 6631861 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3296. Min Act: -0.1700
Data Index: 2859130 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3608. Min Act: -0.1700
Data Index: 6778748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3296. Min Act: -0.1700
Data Index: 7449393 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2983. Min Act: -0.1700
Data Index: 7560687 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2983. Min Act: -0.1700
Data Index: 3968438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2983. Min Act: -0.1700
Data Index: 3388418 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2983. Min Act: -0.1700
Data Index: 7265726 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2983. Min Act: -0.1700
Data Index: 6970649 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2983. Min Act: -0.1700
Data Index: 2923505 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2671. Min Act: -0.1700
Data Index: 3928084 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2983. Min Act: -0.1689
Data Index: 2837897 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2358. Min Act: -0.1700
Data Index: 706495 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2358. Min Act: -0.1700
Data Index: 3631396 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2671. Min Act: -0.1700
Data Index: 2507123 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2671. Min Act: -0.1700
Data Index: 4112972 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19