Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2926 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5808. Min Range: -8.5808
Max Act: 8.5808. Min Act: -0.1700
Data Index: 4440107 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5808. Min Range: -8.5808
Max Act: 8.3933. Min Act: -0.1700
Data Index: 3257189 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5808. Min Range: -8.5808
Max Act: 8.3308. Min Act: -0.1700
Data Index: 13888 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5808. Min Range: -8.5808
Max Act: 8.2058. Min Act: -0.1700
Data Index: 6455863 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5808. Min Range: -8.5808
Max Act: 8.1433. Min Act: -0.1700
Data Index: 7109987 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5808. Min Range: -8.5808
Max Act: 8.0808. Min Act: -0.1700
Data Index: 2826560 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5808. Min Range: -8.5808
Max Act: 8.0496. Min Act: -0.1700
Data Index: 1082551 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.9558. Min Act: -0.1700
Data Index: 3576904 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.9246. Min Act: -0.1700
Data Index: 3289064 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.9246. Min Act: -0.1700
Data Index: 1107806 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.9246. Min Act: -0.1700
Data Index: 6226281 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.8933. Min Act: -0.1700
Data Index: 409743 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.8933. Min Act: -0.1700
Data Index: 8828235 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.8621. Min Act: -0.1700
Data Index: 2250195 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.9246. Min Act: -0.1700
Data Index: 3572868 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.8621. Min Act: -0.1700
Data Index: 4731361 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.8621. Min Act: -0.1700
Data Index: 4845053 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.8308. Min Act: -0.1700
Data Index: 8417767 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.7683. Min Act: -0.1700
Data Index: 942526 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5808. Min Range: -8.5808
Max Act: 7.7371. Min Act: -0.1700
Data Index: 3868603 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19