Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2211 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.9431. Min Act: -0.1700
Data Index: 1514766 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.8806. Min Act: -0.1700
Data Index: 4429777 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.7556. Min Act: -0.1700
Data Index: 4749600 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.6306. Min Act: -0.1700
Data Index: 1933526 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.5056. Min Act: -0.1700
Data Index: 2843143 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.3806. Min Act: -0.1700
Data Index: 2700851 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.3806. Min Act: -0.1700
Data Index: 1737079 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.3181. Min Act: -0.1700
Data Index: 2746251 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.2556. Min Act: -0.1700
Data Index: 3408456 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.1306. Min Act: -0.1700
Data Index: 8488435 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.1931. Min Act: -0.1700
Data Index: 7471134 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.1931. Min Act: -0.1700
Data Index: 1360899 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.1931. Min Act: -0.1700
Data Index: 6840362 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.1931. Min Act: -0.1700
Data Index: 7081668 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.1931. Min Act: -0.1700
Data Index: 3223496 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.1306. Min Act: -0.1700
Data Index: 2890482 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.0681. Min Act: -0.1700
Data Index: 957407 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.0681. Min Act: -0.1700
Data Index: 2473210 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.0681. Min Act: -0.1700
Data Index: 5063380 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9431. Min Range: -9.9431
Max Act: 9.0681. Min Act: -0.1700
Data Index: 6858489 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19