Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6303 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.6765. Min Act: -0.1700
Data Index: 3947062 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.6296. Min Act: -0.1700
Data Index: 6397959 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.6139. Min Act: -0.1700
Data Index: 7796316 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.5357. Min Act: -0.1700
Data Index: 4460475 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.5357. Min Act: -0.1700
Data Index: 7331207 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.5200. Min Act: -0.1700
Data Index: 6579592 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.5043. Min Act: -0.1700
Data Index: 7297314 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4887. Min Act: -0.1700
Data Index: 7395069 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4730. Min Act: -0.1700
Data Index: 85319 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4730. Min Act: -0.1700
Data Index: 8258836 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4887. Min Act: -0.1700
Data Index: 8112247 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4573. Min Act: -0.1700
Data Index: 4199231 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4417. Min Act: -0.1700
Data Index: 2812711 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4417. Min Act: -0.1700
Data Index: 119466 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4103. Min Act: -0.1700
Data Index: 2693253 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.3946. Min Act: -0.1700
Data Index: 8249402 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4103. Min Act: -0.1700
Data Index: 3277816 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4103. Min Act: -0.1700
Data Index: 4142709 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.4103. Min Act: -0.1700
Data Index: 7285147 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6765. Min Range: -3.6765
Max Act: 3.3946. Min Act: -0.1700
Data Index: 56421 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19