Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.5615. Min Act: -0.1700
Data Index: 8380633 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.5302. Min Act: -0.1700
Data Index: 7817107 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.4990. Min Act: -0.1700
Data Index: 5378773 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.4990. Min Act: -0.1700
Data Index: 2638524 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.4677. Min Act: -0.1700
Data Index: 6058229 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.4677. Min Act: -0.1700
Data Index: 261770 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.4365. Min Act: -0.1700
Data Index: 1414529 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3740. Min Act: -0.1699
Data Index: 1219738 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3427. Min Act: -0.1700
Data Index: 7234266 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3427. Min Act: -0.1700
Data Index: 7068464 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3427. Min Act: -0.1700
Data Index: 3835920 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3740. Min Act: -0.1700
Data Index: 7947801 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 7091584 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 5753261 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3427. Min Act: -0.1700
Data Index: 3759008 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 6345266 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2802. Min Act: -0.1700
Data Index: 4485794 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2802. Min Act: -0.1700
Data Index: 4220535 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2802. Min Act: -0.1700
Data Index: 2336046 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2802. Min Act: -0.1700
Data Index: 2876657 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19