Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 603 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1612. Min Range: -7.1612
Max Act: 7.1612. Min Act: -0.1700
Data Index: 4182945 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1612. Min Range: -7.1612
Max Act: 7.1612. Min Act: -0.1700
Data Index: 97144 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.9112. Min Act: -0.1700
Data Index: 7182015 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.8799. Min Act: -0.1700
Data Index: 7704023 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.9424. Min Act: -0.1700
Data Index: 2412878 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.8174. Min Act: -0.1700
Data Index: 1766464 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.7862. Min Act: -0.1700
Data Index: 2519384 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.7549. Min Act: -0.1700
Data Index: 2025800 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.7237. Min Act: -0.1700
Data Index: 7649202 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.6612. Min Act: -0.1700
Data Index: 7492010 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.6924. Min Act: -0.1700
Data Index: 5164285 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.6612. Min Act: -0.1700
Data Index: 1750655 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.6612. Min Act: -0.1700
Data Index: 1317581 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.6299. Min Act: -0.1700
Data Index: 1554583 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.6299. Min Act: -0.1700
Data Index: 17446 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.5987. Min Act: -0.1700
Data Index: 3423408 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.6299. Min Act: -0.1700
Data Index: 5827533 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.5362. Min Act: -0.1700
Data Index: 4233580 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.5674. Min Act: -0.1700
Data Index: 187477 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1612. Min Range: -7.1612
Max Act: 6.5049. Min Act: -0.1700
Data Index: 1578348 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19