Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5761 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.4100. Min Act: -0.1700
Data Index: 5621322 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.3475. Min Act: -0.1700
Data Index: 1453286 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.3163. Min Act: -0.1700
Data Index: 542103 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.2850. Min Act: -0.1700
Data Index: 6606874 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.1913. Min Act: -0.1700
Data Index: 1272719 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.1600. Min Act: -0.1700
Data Index: 6176733 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.0975. Min Act: -0.1700
Data Index: 3913557 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.0975. Min Act: -0.1700
Data Index: 5170882 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.0350. Min Act: -0.1700
Data Index: 319515 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.0350. Min Act: -0.1700
Data Index: 3092331 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.0350. Min Act: -0.1700
Data Index: 4847753 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.0038. Min Act: -0.1700
Data Index: 3073495 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.0038. Min Act: -0.1700
Data Index: 8773082 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4100. Min Range: -7.4100
Max Act: 7.0038. Min Act: -0.1700
Data Index: 8750123 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4100. Min Range: -7.4100
Max Act: 6.9725. Min Act: -0.1700
Data Index: 7396140 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4100. Min Range: -7.4100
Max Act: 6.9725. Min Act: -0.1700
Data Index: 8552188 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4100. Min Range: -7.4100
Max Act: 6.9413. Min Act: -0.1700
Data Index: 660576 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4100. Min Range: -7.4100
Max Act: 6.9100. Min Act: -0.1700
Data Index: 3233134 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4100. Min Range: -7.4100
Max Act: 6.9100. Min Act: -0.1700
Data Index: 7646840 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4100. Min Range: -7.4100
Max Act: 6.9100. Min Act: -0.1700
Data Index: 4255933 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19