Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5434 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0461. Min Range: -5.0461
Max Act: 5.0461. Min Act: -0.1700
Data Index: 4858321 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.9836. Min Act: -0.1700
Data Index: 8500299 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.9836. Min Act: -0.1700
Data Index: 517394 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.9524. Min Act: -0.1700
Data Index: 517402 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.9211. Min Act: -0.1700
Data Index: 7918538 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.8899. Min Act: -0.1700
Data Index: 6792165 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.8586. Min Act: -0.1700
Data Index: 5854890 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.8586. Min Act: -0.1700
Data Index: 3818316 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.8586. Min Act: -0.1700
Data Index: 6126756 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.8274. Min Act: -0.1700
Data Index: 7622349 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.8274. Min Act: -0.1700
Data Index: 3828674 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.7961. Min Act: -0.1700
Data Index: 7622354 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.7961. Min Act: -0.1700
Data Index: 505675 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.7649. Min Act: -0.1700
Data Index: 3775273 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.7336. Min Act: -0.1700
Data Index: 7974839 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.7649. Min Act: -0.1700
Data Index: 2431248 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.7336. Min Act: -0.1700
Data Index: 2726577 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.7336. Min Act: -0.1700
Data Index: 132098 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.7336. Min Act: -0.1700
Data Index: 1110707 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0461. Min Range: -5.0461
Max Act: 4.7336. Min Act: -0.1700
Data Index: 11202 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19