Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5511 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.4085. Min Act: -0.1700
Data Index: 2980876 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.2835. Min Act: -0.1700
Data Index: 5037606 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.2835. Min Act: -0.1700
Data Index: 6553287 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.2835. Min Act: -0.1700
Data Index: 1987282 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.2210. Min Act: -0.1700
Data Index: 2624490 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1585. Min Act: -0.1700
Data Index: 3622761 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.2210. Min Act: -0.1700
Data Index: 4796122 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1585. Min Act: -0.1700
Data Index: 7225023 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1585. Min Act: -0.1700
Data Index: 7443583 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1898. Min Act: -0.1700
Data Index: 2885230 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1898. Min Act: -0.1700
Data Index: 3361065 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1585. Min Act: -0.1700
Data Index: 1422783 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1585. Min Act: -0.1700
Data Index: 1854040 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1585. Min Act: -0.1700
Data Index: 6401568 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1585. Min Act: -0.1700
Data Index: 5541724 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0960. Min Act: -0.1700
Data Index: 3125630 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1272. Min Act: -0.1700
Data Index: 6623771 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.0960. Min Act: -0.1700
Data Index: 7745630 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1272. Min Act: -0.1700
Data Index: 3494189 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4085. Min Range: -4.4085
Max Act: 4.1585. Min Act: -0.1700
Data Index: 3018607 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19