Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5774 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.5882. Min Act: -0.1700
Data Index: 8003797 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.4319. Min Act: -0.1700
Data Index: 8274173 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.4319. Min Act: -0.1700
Data Index: 8274167 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.4319. Min Act: -0.1700
Data Index: 5517381 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.4319. Min Act: -0.1700
Data Index: 3773958 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.4007. Min Act: -0.1700
Data Index: 2269346 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.4007. Min Act: -0.1700
Data Index: 8652903 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.3382. Min Act: -0.1700
Data Index: 8274168 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.3382. Min Act: -0.1700
Data Index: 8003800 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.3382. Min Act: -0.1700
Data Index: 8003784 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.3382. Min Act: -0.1700
Data Index: 33662 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.3069. Min Act: -0.1699
Data Index: 4854294 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.3069. Min Act: -0.1700
Data Index: 8274145 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.3069. Min Act: -0.1700
Data Index: 8003794 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.3069. Min Act: -0.1700
Data Index: 4342322 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.3069. Min Act: -0.1691
Data Index: 3181350 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.2757. Min Act: -0.1698
Data Index: 540061 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.2444. Min Act: -0.1700
Data Index: 8003776 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.2757. Min Act: -0.1700
Data Index: 8003796 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5882. Min Range: -5.5882
Max Act: 5.2757. Min Act: -0.1699
Data Index: 2248133 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19