Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6314 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.5510. Min Act: -0.1700
Data Index: 2485157 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.3947. Min Act: -0.1700
Data Index: 7865314 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.3322. Min Act: -0.1700
Data Index: 8103123 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.3322. Min Act: -0.1700
Data Index: 6683416 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.3010. Min Act: -0.1700
Data Index: 1396773 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.3010. Min Act: -0.1700
Data Index: 5205217 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2385. Min Act: -0.1700
Data Index: 1651521 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2697. Min Act: -0.1700
Data Index: 2007726 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2697. Min Act: -0.1700
Data Index: 8060251 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2697. Min Act: -0.1700
Data Index: 3853611 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2697. Min Act: -0.1700
Data Index: 3616652 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2072. Min Act: -0.1700
Data Index: 4692951 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2385. Min Act: -0.1700
Data Index: 7152692 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2385. Min Act: -0.1700
Data Index: 740073 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2385. Min Act: -0.1700
Data Index: 4193115 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2697. Min Act: -0.1700
Data Index: 2946257 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2385. Min Act: -0.1700
Data Index: 351671 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2385. Min Act: -0.1700
Data Index: 4115887 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2385. Min Act: -0.1700
Data Index: 2236598 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5510. Min Range: -5.5510
Max Act: 5.2072. Min Act: -0.1700
Data Index: 6030965 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19