Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3315 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0086. Min Range: -9.0086
Max Act: 9.0086. Min Act: -0.1700
Data Index: 7168466 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.9461. Min Act: -0.1700
Data Index: 463786 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.6336. Min Act: -0.1700
Data Index: 4171323 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.4461. Min Act: -0.1700
Data Index: 2546494 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.3836. Min Act: -0.1700
Data Index: 2374946 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.2586. Min Act: -0.1700
Data Index: 855412 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.2586. Min Act: -0.1700
Data Index: 2811051 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.2586. Min Act: -0.1700
Data Index: 128336 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.1961. Min Act: -0.1700
Data Index: 4197644 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.1961. Min Act: -0.1700
Data Index: 647664 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.1961. Min Act: -0.1700
Data Index: 4171321 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.1961. Min Act: -0.1700
Data Index: 682048 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.1336. Min Act: -0.1700
Data Index: 5688097 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.1336. Min Act: -0.1700
Data Index: 985377 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.1336. Min Act: -0.1700
Data Index: 4331764 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.0711. Min Act: -0.1700
Data Index: 246856 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.0711. Min Act: -0.1700
Data Index: 731777 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.0711. Min Act: -0.1700
Data Index: 213763 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.0711. Min Act: -0.1700
Data Index: 2599543 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0086. Min Range: -9.0086
Max Act: 8.0711. Min Act: -0.1700
Data Index: 2789429 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19