Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5103 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.8570. Min Act: -0.1700
Data Index: 1720257 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.8570. Min Act: -0.1700
Data Index: 5413936 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.8570. Min Act: -0.1700
Data Index: 2303913 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7945. Min Act: -0.1699
Data Index: 8409698 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7633. Min Act: -0.1700
Data Index: 841229 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7633. Min Act: -0.1700
Data Index: 396863 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7633. Min Act: -0.1697
Data Index: 8716003 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 2818427 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.6695. Min Act: -0.1700
Data Index: 3151087 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 3318807 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 5405791 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 6211289 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 6722023 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7320. Min Act: -0.1700
Data Index: 8435869 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.6695. Min Act: -0.1700
Data Index: 7849805 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 2706133 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 8029298 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.6695. Min Act: -0.1700
Data Index: 5924235 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.6695. Min Act: -0.1700
Data Index: 3762195 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.6695. Min Act: -0.1700
Data Index: 7431259 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19