Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0201. Min Range: -6.0201
Max Act: 6.0201. Min Act: -0.1700
Data Index: 4014936 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.9888. Min Act: -0.1700
Data Index: 651767 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.9576. Min Act: -0.1700
Data Index: 2821687 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.9576. Min Act: -0.1700
Data Index: 8744199 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.9576. Min Act: -0.1700
Data Index: 7907081 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.9576. Min Act: -0.1700
Data Index: 6667242 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.9263. Min Act: -0.1700
Data Index: 5990506 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.8951. Min Act: -0.1700
Data Index: 8393460 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.8951. Min Act: -0.1700
Data Index: 4162338 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.8326. Min Act: -0.1700
Data Index: 613071 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.8638. Min Act: -0.1700
Data Index: 5747879 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.8013. Min Act: -0.1700
Data Index: 3843182 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.7388. Min Act: -0.1700
Data Index: 7985030 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.6763. Min Act: -0.1700
Data Index: 1870771 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.6763. Min Act: -0.1700
Data Index: 8132675 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.6138. Min Act: -0.1700
Data Index: 7306098 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.6138. Min Act: -0.1700
Data Index: 250131 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.5826. Min Act: -0.1700
Data Index: 1017783 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.6138. Min Act: -0.1700
Data Index: 5689171 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0201. Min Range: -6.0201
Max Act: 5.5826. Min Act: -0.1700
Data Index: 3813204 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19