Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6352 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.8262. Min Act: -0.1700
Data Index: 924719 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.8887. Min Act: -0.1700
Data Index: 2200244 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.8262. Min Act: -0.1699
Data Index: 8231892 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.8262. Min Act: -0.1700
Data Index: 3524309 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.7637. Min Act: -0.1700
Data Index: 372547 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.7012. Min Act: -0.1700
Data Index: 2579167 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.6387. Min Act: -0.1700
Data Index: 7667540 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.7012. Min Act: -0.1700
Data Index: 1212276 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.7012. Min Act: -0.1700
Data Index: 4398812 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.5762. Min Act: -0.1700
Data Index: 2034708 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.5762. Min Act: -0.1700
Data Index: 987781 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.5137. Min Act: -0.1700
Data Index: 6264935 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.5762. Min Act: -0.1700
Data Index: 5845480 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.5762. Min Act: -0.1700
Data Index: 8518537 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.5762. Min Act: -0.1700
Data Index: 8326931 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.5762. Min Act: -0.1700
Data Index: 198673 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.5137. Min Act: -0.1700
Data Index: 4073146 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.5137. Min Act: -0.1700
Data Index: 3257947 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.5137. Min Act: -0.1700
Data Index: 4594501 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8887. Min Range: -10.8887
Max Act: 10.5137. Min Act: -0.1700
Data Index: 383329 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19