Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 976 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.9913. Min Act: -0.1700
Data Index: 5323157 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.6475. Min Act: -0.1700
Data Index: 8371746 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.6475. Min Act: -0.1700
Data Index: 6551084 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.5225. Min Act: -0.1700
Data Index: 3637191 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.5225. Min Act: -0.1700
Data Index: 934972 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.5538. Min Act: -0.1700
Data Index: 6102571 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.4600. Min Act: -0.1700
Data Index: 6966536 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.4600. Min Act: -0.1700
Data Index: 7774074 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.4288. Min Act: -0.1700
Data Index: 4386519 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.3975. Min Act: -0.1700
Data Index: 7473257 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.3663. Min Act: -0.1700
Data Index: 3441039 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.3663. Min Act: -0.1700
Data Index: 5643575 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.3350. Min Act: -0.1700
Data Index: 276434 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.3038. Min Act: -0.1700
Data Index: 362191 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.3350. Min Act: -0.1700
Data Index: 6238222 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.3038. Min Act: -0.1700
Data Index: 4479394 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.3038. Min Act: -0.1700
Data Index: 5815323 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.3038. Min Act: -0.1700
Data Index: 3637190 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.2725. Min Act: -0.1700
Data Index: 4396049 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9913. Min Range: -7.9913
Max Act: 7.2725. Min Act: -0.1700
Data Index: 6721837 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19