Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4644 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3728. Min Range: -6.3728
Max Act: 6.3728. Min Act: -0.1700
Data Index: 3601098 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3728. Min Range: -6.3728
Max Act: 6.2166. Min Act: -0.1700
Data Index: 8696064 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3728. Min Range: -6.3728
Max Act: 6.1853. Min Act: -0.1700
Data Index: 264543 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3728. Min Range: -6.3728
Max Act: 6.1853. Min Act: -0.1700
Data Index: 8562464 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3728. Min Range: -6.3728
Max Act: 6.1541. Min Act: -0.1700
Data Index: 2285112 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3728. Min Range: -6.3728
Max Act: 6.0916. Min Act: -0.1700
Data Index: 3917085 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3728. Min Range: -6.3728
Max Act: 6.0603. Min Act: -0.1700
Data Index: 5890725 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3728. Min Range: -6.3728
Max Act: 6.0291. Min Act: -0.1700
Data Index: 8712226 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.9978. Min Act: -0.1700
Data Index: 5750605 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.9666. Min Act: -0.1700
Data Index: 4612180 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.9978. Min Act: -0.1700
Data Index: 2503942 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.9666. Min Act: -0.1700
Data Index: 3958515 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.9353. Min Act: -0.1700
Data Index: 5991970 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.9353. Min Act: -0.1700
Data Index: 4767390 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.9353. Min Act: -0.1700
Data Index: 5981989 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.9041. Min Act: -0.1700
Data Index: 2776868 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.9041. Min Act: -0.1700
Data Index: 7155315 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.8728. Min Act: -0.1700
Data Index: 3352755 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.9041. Min Act: -0.1700
Data Index: 549706 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3728. Min Range: -6.3728
Max Act: 5.8728. Min Act: -0.1700
Data Index: 6458477 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19