Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4533 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3261. Min Range: -5.3261
Max Act: 5.3261. Min Act: -0.1700
Data Index: 3221968 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3261. Min Range: -5.3261
Max Act: 5.1073. Min Act: -0.1700
Data Index: 6592792 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3261. Min Range: -5.3261
Max Act: 5.0448. Min Act: -0.1700
Data Index: 4424416 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3261. Min Range: -5.3261
Max Act: 5.0136. Min Act: -0.1700
Data Index: 1438875 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3261. Min Range: -5.3261
Max Act: 5.0136. Min Act: -0.1700
Data Index: 7433724 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.9198. Min Act: -0.1700
Data Index: 8556187 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.9823. Min Act: -0.1700
Data Index: 617325 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.8573. Min Act: -0.1700
Data Index: 5179799 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.8573. Min Act: -0.1700
Data Index: 5813652 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.8261. Min Act: -0.1700
Data Index: 4798875 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.8261. Min Act: -0.1700
Data Index: 8757538 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.7948. Min Act: -0.1700
Data Index: 1992650 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.7011. Min Act: -0.1700
Data Index: 82325 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.7011. Min Act: -0.1700
Data Index: 3082497 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.7323. Min Act: -0.1700
Data Index: 6038510 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.6698. Min Act: -0.1700
Data Index: 7329107 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.6698. Min Act: -0.1700
Data Index: 8408960 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.6073. Min Act: -0.1700
Data Index: 1490232 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.6073. Min Act: -0.1700
Data Index: 1685693 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3261. Min Range: -5.3261
Max Act: 4.6386. Min Act: -0.1700
Data Index: 5134370 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19