Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2463 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0050. Min Range: -6.0050
Max Act: 6.0050. Min Act: -0.1700
Data Index: 4163071 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.9425. Min Act: -0.1700
Data Index: 2396852 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.9112. Min Act: -0.1700
Data Index: 7554203 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.9112. Min Act: -0.1700
Data Index: 8785669 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.8800. Min Act: -0.1700
Data Index: 7984017 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.8487. Min Act: -0.1700
Data Index: 7245280 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.8175. Min Act: -0.1700
Data Index: 153672 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.8175. Min Act: -0.1700
Data Index: 4119496 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.8175. Min Act: -0.1700
Data Index: 1527113 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.7862. Min Act: -0.1700
Data Index: 7714929 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.7862. Min Act: -0.1700
Data Index: 6441081 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.7862. Min Act: -0.1700
Data Index: 7178006 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.7862. Min Act: -0.1700
Data Index: 4714283 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.7862. Min Act: -0.1700
Data Index: 8583638 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.7550. Min Act: -0.1700
Data Index: 1315017 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.7550. Min Act: -0.1700
Data Index: 5205220 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.7237. Min Act: -0.1700
Data Index: 7306398 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.7237. Min Act: -0.1700
Data Index: 4387454 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.7237. Min Act: -0.1700
Data Index: 5670574 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0050. Min Range: -6.0050
Max Act: 5.6925. Min Act: -0.1700
Data Index: 7569394 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19