Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4807 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.6924. Min Act: -0.1700
Data Index: 905472 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.4736. Min Act: -0.1700
Data Index: 1249452 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.4736. Min Act: -0.1700
Data Index: 3656879 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.4424. Min Act: -0.1700
Data Index: 3731706 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.4111. Min Act: -0.1700
Data Index: 1249453 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.4736. Min Act: -0.1700
Data Index: 6535202 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.4111. Min Act: -0.1700
Data Index: 905475 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.4111. Min Act: -0.1700
Data Index: 2198440 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.3799. Min Act: -0.1700
Data Index: 5903690 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.3174. Min Act: -0.1700
Data Index: 5726863 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.3486. Min Act: -0.1700
Data Index: 5629611 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.3486. Min Act: -0.1700
Data Index: 8350234 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.3486. Min Act: -0.1700
Data Index: 5779751 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.3174. Min Act: -0.1700
Data Index: 6334988 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.3174. Min Act: -0.1700
Data Index: 716110 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.2861. Min Act: -0.1700
Data Index: 1249451 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.2861. Min Act: -0.1700
Data Index: 8232977 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.2861. Min Act: -0.1700
Data Index: 3656882 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.2861. Min Act: -0.1700
Data Index: 566929 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6924. Min Range: -4.6924
Max Act: 4.2549. Min Act: -0.1700
Data Index: 5334857 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19