Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 128 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5741. Min Act: -0.1700
Data Index: 6122668 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5115. Min Act: -0.1700
Data Index: 4176370 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5428. Min Act: -0.1700
Data Index: 5180474 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5428. Min Act: -0.1700
Data Index: 7512110 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5115. Min Act: -0.1700
Data Index: 2573465 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5428. Min Act: -0.1700
Data Index: 7626497 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5115. Min Act: -0.1700
Data Index: 8556417 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4958. Min Act: -0.1700
Data Index: 3248869 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5115. Min Act: -0.1700
Data Index: 1270972 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5115. Min Act: -0.1700
Data Index: 2203066 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5115. Min Act: -0.1700
Data Index: 3037964 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5115. Min Act: -0.1700
Data Index: 306658 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4958. Min Act: -0.1700
Data Index: 5905190 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4958. Min Act: -0.1700
Data Index: 6928193 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4958. Min Act: -0.1700
Data Index: 900861 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.5115. Min Act: -0.1700
Data Index: 2703403 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4802. Min Act: -0.1700
Data Index: 6814400 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4802. Min Act: -0.1700
Data Index: 7169573 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4802. Min Act: -0.1700
Data Index: 7072172 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5741. Min Range: -3.5741
Max Act: 3.4802. Min Act: -0.1700
Data Index: 1688245 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19