Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.6040. Min Act: -0.1700
Data Index: 4261667 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.5883. Min Act: -0.1700
Data Index: 4261666 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.5727. Min Act: -0.1700
Data Index: 2706238 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4787. Min Act: -0.1700
Data Index: 8318358 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4160. Min Act: -0.1700
Data Index: 6982265 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4003. Min Act: -0.1700
Data Index: 761599 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.3690. Min Act: -0.1700
Data Index: 8714303 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.3062. Min Act: -0.1700
Data Index: 5612723 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2905. Min Act: -0.1700
Data Index: 2262558 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2748. Min Act: -0.1700
Data Index: 4707270 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2905. Min Act: -0.1700
Data Index: 4520879 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2434. Min Act: -0.1700
Data Index: 3890980 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2591. Min Act: -0.1700
Data Index: 2065738 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2434. Min Act: -0.1700
Data Index: 1553190 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2591. Min Act: -0.1700
Data Index: 1015811 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2434. Min Act: -0.1700
Data Index: 8613628 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2434. Min Act: -0.1700
Data Index: 6118296 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2434. Min Act: -0.1700
Data Index: 4529452 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2434. Min Act: -0.1700
Data Index: 8045439 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2277. Min Act: -0.1700
Data Index: 1056320 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19