Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.9041. Min Act: -0.1700
Data Index: 5899638 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.8729. Min Act: -0.1700
Data Index: 491173 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 8455014 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 3642836 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7479. Min Act: -0.1700
Data Index: 2585314 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7166. Min Act: -0.1700
Data Index: 3377322 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7166. Min Act: -0.1700
Data Index: 6633687 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.6854. Min Act: -0.1700
Data Index: 6359208 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.6854. Min Act: -0.1700
Data Index: 2709109 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.5916. Min Act: -0.1700
Data Index: 1958441 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.6229. Min Act: -0.1700
Data Index: 5855923 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.6229. Min Act: -0.1700
Data Index: 1206008 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.5916. Min Act: -0.1700
Data Index: 8144653 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.5916. Min Act: -0.1700
Data Index: 8343604 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.5604. Min Act: -0.1700
Data Index: 6222777 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.5604. Min Act: -0.1700
Data Index: 4573639 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.5604. Min Act: -0.1700
Data Index: 8461818 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.5291. Min Act: -0.1700
Data Index: 1382894 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.4979. Min Act: -0.1700
Data Index: 465119 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.5291. Min Act: -0.1700
Data Index: 6083551 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19