Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3363 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.9402. Min Act: -0.1700
Data Index: 887324 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.7527. Min Act: -0.1700
Data Index: 7180363 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.6902. Min Act: -0.1700
Data Index: 7418081 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.6277. Min Act: -0.1700
Data Index: 1645871 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.5652. Min Act: -0.1700
Data Index: 4161531 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.3777. Min Act: -0.1700
Data Index: 5156844 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.3777. Min Act: -0.1700
Data Index: 4352826 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.3152. Min Act: -0.1700
Data Index: 343493 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.3152. Min Act: -0.1700
Data Index: 4981721 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.1902. Min Act: -0.1700
Data Index: 528149 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.2527. Min Act: -0.1700
Data Index: 7864018 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.1277. Min Act: -0.1700
Data Index: 8464662 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.1277. Min Act: -0.1700
Data Index: 8661241 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.0652. Min Act: -0.1700
Data Index: 4870136 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.0652. Min Act: -0.1700
Data Index: 7028092 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.0027. Min Act: -0.1700
Data Index: 822574 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.0027. Min Act: -0.1700
Data Index: 460369 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.0027. Min Act: -0.1700
Data Index: 1431552 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9402. Min Range: -9.9402
Max Act: 9.0652. Min Act: -0.1700
Data Index: 4439843 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9402. Min Range: -9.9402
Max Act: 8.9402. Min Act: -0.1700
Data Index: 5045247 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19