Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3337 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3576. Min Range: -9.3576
Max Act: 9.3576. Min Act: -0.1700
Data Index: 4305476 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3576. Min Range: -9.3576
Max Act: 8.4826. Min Act: -0.1700
Data Index: 5942042 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3576. Min Range: -9.3576
Max Act: 8.2326. Min Act: -0.1700
Data Index: 8462524 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3576. Min Range: -9.3576
Max Act: 8.1701. Min Act: -0.1700
Data Index: 6044954 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3576. Min Range: -9.3576
Max Act: 8.1076. Min Act: -0.1700
Data Index: 163116 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3576. Min Range: -9.3576
Max Act: 8.1076. Min Act: -0.1700
Data Index: 2833273 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3576. Min Range: -9.3576
Max Act: 8.1076. Min Act: -0.1700
Data Index: 5427720 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3576. Min Range: -9.3576
Max Act: 8.0451. Min Act: -0.1700
Data Index: 6618052 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3576. Min Range: -9.3576
Max Act: 8.0451. Min Act: -0.1700
Data Index: 4982056 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3576. Min Range: -9.3576
Max Act: 7.9826. Min Act: -0.1700
Data Index: 748170 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3576. Min Range: -9.3576
Max Act: 7.9826. Min Act: -0.1700
Data Index: 8380430 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3576. Min Range: -9.3576
Max Act: 7.9826. Min Act: -0.1700
Data Index: 4676267 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3576. Min Range: -9.3576
Max Act: 7.9201. Min Act: -0.1700
Data Index: 4216225 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3576. Min Range: -9.3576
Max Act: 7.9201. Min Act: -0.1700
Data Index: 8565958 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3576. Min Range: -9.3576
Max Act: 7.9201. Min Act: -0.1700
Data Index: 3891182 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3576. Min Range: -9.3576
Max Act: 7.8576. Min Act: -0.1700
Data Index: 2431763 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3576. Min Range: -9.3576
Max Act: 7.8576. Min Act: -0.1700
Data Index: 2767712 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3576. Min Range: -9.3576
Max Act: 7.7951. Min Act: -0.1700
Data Index: 1705861 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3576. Min Range: -9.3576
Max Act: 7.8576. Min Act: -0.1700
Data Index: 5454562 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3576. Min Range: -9.3576
Max Act: 7.8576. Min Act: -0.1700
Data Index: 8344158 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19