Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.9374. Min Act: -0.1700
Data Index: 7385548 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.6874. Min Act: -0.1700
Data Index: 3389703 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.7186. Min Act: -0.1700
Data Index: 7731685 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.7186. Min Act: -0.1700
Data Index: 7551239 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.5311. Min Act: -0.1700
Data Index: 8003174 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.5311. Min Act: -0.1700
Data Index: 6605082 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.4999. Min Act: -0.1700
Data Index: 7734951 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.4999. Min Act: -0.1700
Data Index: 5686353 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.4686. Min Act: -0.1700
Data Index: 3347768 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.4686. Min Act: -0.1700
Data Index: 7298737 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.4999. Min Act: -0.1700
Data Index: 4423192 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.4061. Min Act: -0.1700
Data Index: 1702786 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.4061. Min Act: -0.1700
Data Index: 4641977 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.3436. Min Act: -0.1700
Data Index: 8582272 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.3124. Min Act: -0.1700
Data Index: 5948356 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.3124. Min Act: -0.1700
Data Index: 2105795 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.3124. Min Act: -0.1700
Data Index: 2753526 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.3124. Min Act: -0.1700
Data Index: 7867058 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.2811. Min Act: -0.1700
Data Index: 2709951 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9374. Min Range: -7.9374
Max Act: 7.2499. Min Act: -0.1700
Data Index: 3538147 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19