Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1618 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4119. Min Range: -5.4119
Max Act: 5.4119. Min Act: -0.1700
Data Index: 5035096 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4119. Min Range: -5.4119
Max Act: 5.3182. Min Act: -0.1700
Data Index: 8545268 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4119. Min Range: -5.4119
Max Act: 5.2557. Min Act: -0.1700
Data Index: 5199895 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4119. Min Range: -5.4119
Max Act: 5.0994. Min Act: -0.1700
Data Index: 6312221 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4119. Min Range: -5.4119
Max Act: 5.0369. Min Act: -0.1700
Data Index: 3312770 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4119. Min Range: -5.4119
Max Act: 5.0682. Min Act: -0.1700
Data Index: 40717 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4119. Min Range: -5.4119
Max Act: 5.0057. Min Act: -0.1700
Data Index: 5436789 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.9744. Min Act: -0.1700
Data Index: 637087 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.9119. Min Act: -0.1700
Data Index: 293798 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.9432. Min Act: -0.1700
Data Index: 2135733 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.9432. Min Act: -0.1699
Data Index: 3402842 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.9432. Min Act: -0.1700
Data Index: 5184181 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.9119. Min Act: -0.1700
Data Index: 6292571 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.8807. Min Act: -0.1700
Data Index: 7208541 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.8807. Min Act: -0.1700
Data Index: 5640680 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.8494. Min Act: -0.1700
Data Index: 6625628 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.8807. Min Act: -0.1700
Data Index: 3170132 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.8494. Min Act: -0.1700
Data Index: 3331985 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.8182. Min Act: -0.1700
Data Index: 4636725 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4119. Min Range: -5.4119
Max Act: 4.7869. Min Act: -0.1700
Data Index: 2684634 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19