Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 683 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.5946. Min Act: -0.1700
Data Index: 440336 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.5009. Min Act: -0.1700
Data Index: 8161102 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.4384. Min Act: -0.1700
Data Index: 5765528 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.3759. Min Act: -0.1700
Data Index: 4442384 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.4071. Min Act: -0.1700
Data Index: 4212885 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.4071. Min Act: -0.1700
Data Index: 6467294 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.3759. Min Act: -0.1700
Data Index: 4351341 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.3446. Min Act: -0.1700
Data Index: 8460292 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.3446. Min Act: -0.1700
Data Index: 8721690 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.3446. Min Act: -0.1700
Data Index: 7589028 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.3134. Min Act: -0.1700
Data Index: 4814269 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.3134. Min Act: -0.1700
Data Index: 5500956 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.3134. Min Act: -0.1700
Data Index: 3223713 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.3134. Min Act: -0.1700
Data Index: 4630641 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.2821. Min Act: -0.1700
Data Index: 8106414 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.3134. Min Act: -0.1700
Data Index: 7528370 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.2821. Min Act: -0.1700
Data Index: 632974 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.2509. Min Act: -0.1700
Data Index: 971812 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.2821. Min Act: -0.1700
Data Index: 393024 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5946. Min Range: -6.5946
Max Act: 6.2821. Min Act: -0.1700
Data Index: 8471518 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19