Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4359 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.8885. Min Act: -0.1700
Data Index: 234605 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.9198. Min Act: -0.1700
Data Index: 4595490 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.9198. Min Act: -0.1700
Data Index: 6830420 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.9198. Min Act: -0.1700
Data Index: 5403762 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.9510. Min Act: -0.1700
Data Index: 5942154 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.8885. Min Act: -0.1700
Data Index: 965919 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.8885. Min Act: -0.1700
Data Index: 2005565 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.8572. Min Act: -0.1700
Data Index: 4605501 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.8572. Min Act: -0.1700
Data Index: 6198735 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.8572. Min Act: -0.1700
Data Index: 5882141 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.8260. Min Act: -0.1700
Data Index: 1328217 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.8572. Min Act: -0.1700
Data Index: 4102153 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.7947. Min Act: -0.1700
Data Index: 5859225 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.8260. Min Act: -0.1700
Data Index: 5568267 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.8260. Min Act: -0.1700
Data Index: 7742425 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.7947. Min Act: -0.1700
Data Index: 3165313 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.7947. Min Act: -0.1700
Data Index: 2890293 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.7947. Min Act: -0.1700
Data Index: 4068068 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.7947. Min Act: -0.1700
Data Index: 6700579 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9510. Min Range: -3.9510
Max Act: 3.7947. Min Act: -0.1700
Data Index: 3631935 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19