Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.3608. Min Act: -0.1700
Data Index: 3312669 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.3608. Min Act: -0.1700
Data Index: 4843183 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.3608. Min Act: -0.1700
Data Index: 828157 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.3295. Min Act: -0.1700
Data Index: 4537053 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.3608. Min Act: -0.1700
Data Index: 1068280 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.3295. Min Act: -0.1700
Data Index: 8550791 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2983. Min Act: -0.1700
Data Index: 4875610 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2670. Min Act: -0.1700
Data Index: 7379132 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2670. Min Act: -0.1700
Data Index: 161627 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2670. Min Act: -0.1700
Data Index: 7405862 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2670. Min Act: -0.1700
Data Index: 6723565 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2358. Min Act: -0.1700
Data Index: 5024026 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2358. Min Act: -0.1700
Data Index: 2324188 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2358. Min Act: -0.1700
Data Index: 4731849 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2358. Min Act: -0.1700
Data Index: 1478728 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2045. Min Act: -0.1700
Data Index: 339654 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2358. Min Act: -0.1700
Data Index: 999253 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2358. Min Act: -0.1700
Data Index: 5325644 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2358. Min Act: -0.1700
Data Index: 6008745 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3608. Min Range: -6.3608
Max Act: 6.2045. Min Act: -0.1700
Data Index: 1085242 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19