Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4737 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0320. Min Range: -5.0320
Max Act: 5.0320. Min Act: -0.1700
Data Index: 6497576 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0320. Min Range: -5.0320
Max Act: 5.0320. Min Act: -0.1700
Data Index: 4041909 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0320. Min Range: -5.0320
Max Act: 5.0320. Min Act: -0.1700
Data Index: 7469110 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0320. Min Range: -5.0320
Max Act: 5.0320. Min Act: -0.1700
Data Index: 3347418 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0320. Min Range: -5.0320
Max Act: 5.0008. Min Act: -0.1700
Data Index: 6812080 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0320. Min Range: -5.0320
Max Act: 5.0008. Min Act: -0.1700
Data Index: 2531636 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.9383. Min Act: -0.1700
Data Index: 6099818 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.9070. Min Act: -0.1700
Data Index: 4163849 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.9695. Min Act: -0.1700
Data Index: 2036523 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.9070. Min Act: -0.1700
Data Index: 6463848 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.9070. Min Act: -0.1700
Data Index: 1881524 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.8758. Min Act: -0.1700
Data Index: 1551218 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.8758. Min Act: -0.1700
Data Index: 7860305 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.9070. Min Act: -0.1700
Data Index: 3659634 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.8758. Min Act: -0.1700
Data Index: 5931969 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.8445. Min Act: -0.1700
Data Index: 7807028 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.8133. Min Act: -0.1700
Data Index: 2244133 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.8445. Min Act: -0.1700
Data Index: 7297748 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.8445. Min Act: -0.1700
Data Index: 4304052 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0320. Min Range: -5.0320
Max Act: 4.8133. Min Act: -0.1700
Data Index: 4480749 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19