Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5385 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4601. Min Range: -7.4601
Max Act: 7.4601. Min Act: -0.1700
Data Index: 2484298 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4601. Min Range: -7.4601
Max Act: 7.4601. Min Act: -0.1700
Data Index: 1799373 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4601. Min Range: -7.4601
Max Act: 7.3976. Min Act: -0.1700
Data Index: 4471458 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4601. Min Range: -7.4601
Max Act: 7.3038. Min Act: -0.1700
Data Index: 6801739 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4601. Min Range: -7.4601
Max Act: 7.0226. Min Act: -0.1700
Data Index: 6141752 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.9913. Min Act: -0.1700
Data Index: 5150411 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.9913. Min Act: -0.1700
Data Index: 6538266 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.9288. Min Act: -0.1700
Data Index: 4209266 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.8663. Min Act: -0.1700
Data Index: 7973967 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.8351. Min Act: -0.1700
Data Index: 1459987 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.8038. Min Act: -0.1700
Data Index: 2707270 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.8038. Min Act: -0.1700
Data Index: 3717019 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.7726. Min Act: -0.1700
Data Index: 3941567 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.7726. Min Act: -0.1700
Data Index: 4812541 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.7726. Min Act: -0.1700
Data Index: 7607628 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.7413. Min Act: -0.1700
Data Index: 4966896 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.7413. Min Act: -0.1700
Data Index: 7818943 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.7413. Min Act: -0.1700
Data Index: 5234676 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.7101. Min Act: -0.1700
Data Index: 71834 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4601. Min Range: -7.4601
Max Act: 6.7101. Min Act: -0.1700
Data Index: 4376285 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19