Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.7166. Min Act: -0.1700
Data Index: 2185403 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.5916. Min Act: -0.1700
Data Index: 283663 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.5291. Min Act: -0.1700
Data Index: 4225683 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.5291. Min Act: -0.1700
Data Index: 3929132 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.4041. Min Act: -0.1700
Data Index: 4604342 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.4041. Min Act: -0.1700
Data Index: 3335387 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.3416. Min Act: -0.1700
Data Index: 2334201 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.3416. Min Act: -0.1700
Data Index: 3233527 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.2791. Min Act: -0.1700
Data Index: 3753520 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.2791. Min Act: -0.1700
Data Index: 6711719 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.2791. Min Act: -0.1700
Data Index: 6892182 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.2791. Min Act: -0.1700
Data Index: 5663287 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.2791. Min Act: -0.1700
Data Index: 5595840 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.2166. Min Act: -0.1700
Data Index: 6057550 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.2791. Min Act: -0.1700
Data Index: 2746224 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.2166. Min Act: -0.1700
Data Index: 2417779 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.2166. Min Act: -0.1700
Data Index: 4892559 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.2166. Min Act: -0.1700
Data Index: 1257940 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.1541. Min Act: -0.1700
Data Index: 7935623 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7166. Min Range: -9.7166
Max Act: 9.2166. Min Act: -0.1700
Data Index: 6506723 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19