Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5343. Min Range: -10.5343
Max Act: 10.5343. Min Act: -0.1700
Data Index: 7991036 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.9718. Min Act: -0.1700
Data Index: 4560800 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5343. Min Range: -10.5343
Max Act: 10.0343. Min Act: -0.1700
Data Index: 99202 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5343. Min Range: -10.5343
Max Act: 10.0343. Min Act: -0.1700
Data Index: 2556191 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5343. Min Range: -10.5343
Max Act: 10.0343. Min Act: -0.1700
Data Index: 3622186 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.9093. Min Act: -0.1700
Data Index: 6135071 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.9093. Min Act: -0.1700
Data Index: 3054557 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.9093. Min Act: -0.1700
Data Index: 7409712 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.8468. Min Act: -0.1700
Data Index: 6457521 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.8468. Min Act: -0.1700
Data Index: 5945095 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.8468. Min Act: -0.1700
Data Index: 3720674 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.8468. Min Act: -0.1700
Data Index: 431554 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.7843. Min Act: -0.1700
Data Index: 466598 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.7218. Min Act: -0.1700
Data Index: 7024904 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.7218. Min Act: -0.1700
Data Index: 6433519 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.6593. Min Act: -0.1700
Data Index: 4037583 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.6593. Min Act: -0.1700
Data Index: 8790769 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.6593. Min Act: -0.1700
Data Index: 8397264 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.5968. Min Act: -0.1700
Data Index: 4765303 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5343. Min Range: -10.5343
Max Act: 9.5968. Min Act: -0.1700
Data Index: 5727912 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19