Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4583 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.5396. Min Act: -0.1700
Data Index: 6631667 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.5396. Min Act: -0.1700
Data Index: 6385535 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.4771. Min Act: -0.1700
Data Index: 6229478 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.4146. Min Act: -0.1700
Data Index: 2490956 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.4146. Min Act: -0.1700
Data Index: 3573034 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.3208. Min Act: -0.1700
Data Index: 379620 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.3208. Min Act: -0.1700
Data Index: 4617667 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.3521. Min Act: -0.1700
Data Index: 1579197 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.2896. Min Act: -0.1700
Data Index: 8075217 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.2896. Min Act: -0.1700
Data Index: 3869668 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.2896. Min Act: -0.1700
Data Index: 3663726 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.2896. Min Act: -0.1700
Data Index: 5759666 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.2583. Min Act: -0.1700
Data Index: 6070727 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.2583. Min Act: -0.1700
Data Index: 5566644 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.2583. Min Act: -0.1700
Data Index: 3418365 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.2583. Min Act: -0.1700
Data Index: 6935414 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.2271. Min Act: -0.1700
Data Index: 6963623 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.2271. Min Act: -0.1700
Data Index: 1605713 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.2271. Min Act: -0.1700
Data Index: 4809854 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5396. Min Range: -5.5396
Max Act: 5.1958. Min Act: -0.1700
Data Index: 1498962 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19