Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2652 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4464. Min Range: -7.4464
Max Act: 7.4464. Min Act: -0.1700
Data Index: 4780053 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.9151. Min Act: -0.1700
Data Index: 6238032 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.8839. Min Act: -0.1700
Data Index: 4222250 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.8526. Min Act: -0.1700
Data Index: 4104556 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.8214. Min Act: -0.1700
Data Index: 4790556 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.7276. Min Act: -0.1700
Data Index: 4618729 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.7276. Min Act: -0.1700
Data Index: 3537656 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.6964. Min Act: -0.1700
Data Index: 465881 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.6964. Min Act: -0.1700
Data Index: 7127116 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.6651. Min Act: -0.1700
Data Index: 639396 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.6651. Min Act: -0.1700
Data Index: 1858559 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.6651. Min Act: -0.1700
Data Index: 1027242 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.6339. Min Act: -0.1700
Data Index: 3106924 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.6026. Min Act: -0.1700
Data Index: 1723191 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.5714. Min Act: -0.1700
Data Index: 680017 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.5401. Min Act: -0.1700
Data Index: 1727575 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.5089. Min Act: -0.1700
Data Index: 3938908 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.5401. Min Act: -0.1700
Data Index: 4725769 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.5089. Min Act: -0.1700
Data Index: 513102 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4464. Min Range: -7.4464
Max Act: 6.4776. Min Act: -0.1700
Data Index: 4659673 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19