Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.6144. Min Act: -0.1700
Data Index: 2874850 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.5207. Min Act: -0.1700
Data Index: 8369313 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.5207. Min Act: -0.1700
Data Index: 7299768 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.4894. Min Act: -0.1700
Data Index: 4375997 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.4894. Min Act: -0.1700
Data Index: 7020910 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.4894. Min Act: -0.1700
Data Index: 8578105 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.4582. Min Act: -0.1700
Data Index: 1646708 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.4582. Min Act: -0.1700
Data Index: 4636347 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.3957. Min Act: -0.1700
Data Index: 3841174 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.4582. Min Act: -0.1700
Data Index: 5688930 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.4269. Min Act: -0.1700
Data Index: 2479293 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.4269. Min Act: -0.1700
Data Index: 4680134 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.3957. Min Act: -0.1700
Data Index: 199895 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.3957. Min Act: -0.1700
Data Index: 6681372 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.3332. Min Act: -0.1700
Data Index: 1897982 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.3332. Min Act: -0.1700
Data Index: 8116066 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.3644. Min Act: -0.1700
Data Index: 5019367 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.3644. Min Act: -0.1700
Data Index: 8323081 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.3332. Min Act: -0.1700
Data Index: 4743680 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6144. Min Range: -5.6144
Max Act: 5.3332. Min Act: -0.1700
Data Index: 7816608 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19