Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 11 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.7596. Min Act: -0.1700
Data Index: 4714122 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.7283. Min Act: -0.1700
Data Index: 5911131 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.7596. Min Act: -0.1700
Data Index: 1980317 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.7283. Min Act: -0.1700
Data Index: 1224929 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.7283. Min Act: -0.1700
Data Index: 3546627 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.7283. Min Act: -0.1700
Data Index: 8113801 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6971. Min Act: -0.1700
Data Index: 8178365 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6971. Min Act: -0.1700
Data Index: 5759069 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6658. Min Act: -0.1700
Data Index: 6784201 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6971. Min Act: -0.1700
Data Index: 6579316 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6658. Min Act: -0.1700
Data Index: 1568977 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6971. Min Act: -0.1700
Data Index: 3812114 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6346. Min Act: -0.1700
Data Index: 6488805 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6971. Min Act: -0.1700
Data Index: 6227157 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6658. Min Act: -0.1700
Data Index: 2995091 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6971. Min Act: -0.1700
Data Index: 1116347 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6658. Min Act: -0.1700
Data Index: 4493384 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6971. Min Act: -0.1700
Data Index: 40402 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6658. Min Act: -0.1700
Data Index: 4957877 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7596. Min Range: -5.7596
Max Act: 5.6971. Min Act: -0.1700
Data Index: 1286864 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19