Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5734 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.3939. Min Act: -0.1700
Data Index: 630110 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.3626. Min Act: -0.1700
Data Index: 4671343 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.3001. Min Act: -0.1700
Data Index: 1549695 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.2064. Min Act: -0.1700
Data Index: 1328094 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.1126. Min Act: -0.1700
Data Index: 3241380 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.0814. Min Act: -0.1700
Data Index: 2948695 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.0814. Min Act: -0.1700
Data Index: 4895144 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.0501. Min Act: -0.1700
Data Index: 259385 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.1126. Min Act: -0.1700
Data Index: 2832659 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.0814. Min Act: -0.1700
Data Index: 6466250 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.0189. Min Act: -0.1700
Data Index: 4946285 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.0189. Min Act: -0.1700
Data Index: 7650762 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.0189. Min Act: -0.1700
Data Index: 5701508 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.0189. Min Act: -0.1700
Data Index: 6095820 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.0189. Min Act: -0.1700
Data Index: 290961 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3939. Min Range: -6.3939
Max Act: 5.9876. Min Act: -0.1700
Data Index: 3010898 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3939. Min Range: -6.3939
Max Act: 6.0189. Min Act: -0.1700
Data Index: 2890287 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3939. Min Range: -6.3939
Max Act: 5.9876. Min Act: -0.1700
Data Index: 399798 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3939. Min Range: -6.3939
Max Act: 5.9564. Min Act: -0.1700
Data Index: 76305 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3939. Min Range: -6.3939
Max Act: 5.9564. Min Act: -0.1700
Data Index: 4614707 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19