Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3938 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.2466. Min Act: -0.1700
Data Index: 8484415 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.2154. Min Act: -0.1700
Data Index: 6313732 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.2154. Min Act: -0.1700
Data Index: 6312910 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.2154. Min Act: -0.1700
Data Index: 8669040 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.1841. Min Act: -0.1700
Data Index: 3384149 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.1841. Min Act: -0.1700
Data Index: 615297 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.1529. Min Act: -0.1700
Data Index: 6130473 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.1216. Min Act: -0.1700
Data Index: 1203029 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.1529. Min Act: -0.1700
Data Index: 4862205 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.1216. Min Act: -0.1700
Data Index: 2777904 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.1216. Min Act: -0.1700
Data Index: 2882708 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.0904. Min Act: -0.1700
Data Index: 3034431 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.0591. Min Act: -0.1700
Data Index: 1791926 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.0591. Min Act: -0.1700
Data Index: 3290051 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.0591. Min Act: -0.1700
Data Index: 7578349 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.0904. Min Act: -0.1700
Data Index: 4488756 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.0904. Min Act: -0.1700
Data Index: 6990058 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.0904. Min Act: -0.1700
Data Index: 1355985 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.0904. Min Act: -0.1700
Data Index: 5003714 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2466. Min Range: -4.2466
Max Act: 4.0904. Min Act: -0.1700
Data Index: 1626252 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19