Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3181 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.9612. Min Act: -0.1700
Data Index: 2412066 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.8049. Min Act: -0.1700
Data Index: 7017021 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.5862. Min Act: -0.1700
Data Index: 7864691 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.5862. Min Act: -0.1700
Data Index: 3199718 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.5862. Min Act: -0.1700
Data Index: 1649847 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.5549. Min Act: -0.1700
Data Index: 1929074 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.5549. Min Act: -0.1700
Data Index: 2675505 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.5862. Min Act: -0.1700
Data Index: 8003327 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.5237. Min Act: -0.1700
Data Index: 7491717 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.5237. Min Act: -0.1700
Data Index: 303151 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.5237. Min Act: -0.1700
Data Index: 1627117 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.5549. Min Act: -0.1700
Data Index: 271064 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.4924. Min Act: -0.1700
Data Index: 928972 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.4924. Min Act: -0.1700
Data Index: 1516326 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.4924. Min Act: -0.1700
Data Index: 7976361 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.4299. Min Act: -0.1700
Data Index: 5048160 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.3987. Min Act: -0.1700
Data Index: 500140 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.3987. Min Act: -0.1700
Data Index: 7993117 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.3987. Min Act: -0.1700
Data Index: 4765058 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9612. Min Range: -6.9612
Max Act: 6.3362. Min Act: -0.1700
Data Index: 1066612 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19