Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3820. Min Range: -8.3820
Max Act: 8.3820. Min Act: -0.1700
Data Index: 4176712 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3820. Min Range: -8.3820
Max Act: 8.2570. Min Act: -0.1700
Data Index: 7596332 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.9445. Min Act: -0.1700
Data Index: 5656821 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.8820. Min Act: -0.1700
Data Index: 2744263 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.8820. Min Act: -0.1700
Data Index: 633632 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.8195. Min Act: -0.1700
Data Index: 4071866 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.8195. Min Act: -0.1700
Data Index: 4156396 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.7570. Min Act: -0.1700
Data Index: 1069112 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.7258. Min Act: -0.1700
Data Index: 1958853 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.7570. Min Act: -0.1700
Data Index: 6608922 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.6945. Min Act: -0.1700
Data Index: 3121079 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.6633. Min Act: -0.1700
Data Index: 6359907 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.6633. Min Act: -0.1700
Data Index: 8788365 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.6320. Min Act: -0.1700
Data Index: 8586571 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.6320. Min Act: -0.1700
Data Index: 8007759 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.6008. Min Act: -0.1700
Data Index: 3121077 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.5695. Min Act: -0.1700
Data Index: 1921023 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.5695. Min Act: -0.1700
Data Index: 3705900 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.5695. Min Act: -0.1700
Data Index: 5811409 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3820. Min Range: -8.3820
Max Act: 7.5695. Min Act: -0.1700
Data Index: 757193 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19