Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4761 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.5990. Min Act: -0.1700
Data Index: 4323679 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.3802. Min Act: -0.1700
Data Index: 7170046 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.3490. Min Act: -0.1700
Data Index: 3309005 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.3490. Min Act: -0.1700
Data Index: 6588058 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.2240. Min Act: -0.1700
Data Index: 7924773 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.1927. Min Act: -0.1700
Data Index: 155937 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.1302. Min Act: -0.1700
Data Index: 2039094 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0989. Min Act: -0.1700
Data Index: 7653382 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0989. Min Act: -0.1700
Data Index: 8648716 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0677. Min Act: -0.1700
Data Index: 1989279 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0677. Min Act: -0.1700
Data Index: 1314149 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0677. Min Act: -0.1700
Data Index: 4403238 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0677. Min Act: -0.1700
Data Index: 3342231 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0677. Min Act: -0.1700
Data Index: 3716893 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0677. Min Act: -0.1700
Data Index: 209192 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0364. Min Act: -0.1700
Data Index: 4143622 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0364. Min Act: -0.1700
Data Index: 412226 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0052. Min Act: -0.1700
Data Index: 6134053 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0052. Min Act: -0.1700
Data Index: 990502 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5990. Min Range: -4.5990
Max Act: 4.0052. Min Act: -0.1700
Data Index: 7419858 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19