Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2840 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0279. Min Range: -5.0279
Max Act: 5.0279. Min Act: -0.1700
Data Index: 1083956 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.8717. Min Act: -0.1700
Data Index: 967925 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.8717. Min Act: -0.1700
Data Index: 2115860 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.8404. Min Act: -0.1700
Data Index: 188602 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.8404. Min Act: -0.1700
Data Index: 3083869 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.8404. Min Act: -0.1700
Data Index: 6624485 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.8092. Min Act: -0.1700
Data Index: 5474507 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7779. Min Act: -0.1700
Data Index: 6741949 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7467. Min Act: -0.1700
Data Index: 4723367 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7779. Min Act: -0.1700
Data Index: 2348484 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7779. Min Act: -0.1700
Data Index: 5806650 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7467. Min Act: -0.1700
Data Index: 7044047 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7154. Min Act: -0.1700
Data Index: 2092010 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7154. Min Act: -0.1700
Data Index: 1936745 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7154. Min Act: -0.1700
Data Index: 6598612 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7154. Min Act: -0.1700
Data Index: 7505278 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7154. Min Act: -0.1700
Data Index: 6236506 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7154. Min Act: -0.1700
Data Index: 427136 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7154. Min Act: -0.1700
Data Index: 538146 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0279. Min Range: -5.0279
Max Act: 4.7154. Min Act: -0.1700
Data Index: 8792008 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19