Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2769 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.6165. Min Act: -0.1700
Data Index: 4595870 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.4290. Min Act: -0.1700
Data Index: 1966778 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.3040. Min Act: -0.1700
Data Index: 5557554 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.2728. Min Act: -0.1700
Data Index: 8630208 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.1790. Min Act: -0.1700
Data Index: 5505188 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.1478. Min Act: -0.1700
Data Index: 5577490 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.1165. Min Act: -0.1700
Data Index: 2949086 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.1165. Min Act: -0.1700
Data Index: 7255670 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.1165. Min Act: -0.1700
Data Index: 3327337 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.0853. Min Act: -0.1700
Data Index: 4976011 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.0540. Min Act: -0.1700
Data Index: 1841920 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6165. Min Range: -7.6165
Max Act: 7.0228. Min Act: -0.1700
Data Index: 2694 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6165. Min Range: -7.6165
Max Act: 6.9603. Min Act: -0.1700
Data Index: 6668734 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6165. Min Range: -7.6165
Max Act: 6.9603. Min Act: -0.1700
Data Index: 3028132 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6165. Min Range: -7.6165
Max Act: 6.8978. Min Act: -0.1700
Data Index: 335152 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6165. Min Range: -7.6165
Max Act: 6.9290. Min Act: -0.1700
Data Index: 844636 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6165. Min Range: -7.6165
Max Act: 6.9290. Min Act: -0.1700
Data Index: 1567977 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6165. Min Range: -7.6165
Max Act: 6.9290. Min Act: -0.1700
Data Index: 6255088 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6165. Min Range: -7.6165
Max Act: 6.9290. Min Act: -0.1700
Data Index: 14366 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6165. Min Range: -7.6165
Max Act: 6.9290. Min Act: -0.1700
Data Index: 2940133 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19