Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.5920. Min Act: -0.1700
Data Index: 5527806 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.5598. Min Act: -0.1700
Data Index: 8374125 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.5436. Min Act: -0.1700
Data Index: 6173860 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.5275. Min Act: -0.1700
Data Index: 1914633 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.5275. Min Act: -0.1700
Data Index: 3209187 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.5113. Min Act: -0.1700
Data Index: 2934192 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.5113. Min Act: -0.1700
Data Index: 5303052 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4789. Min Act: -0.1700
Data Index: 8061568 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4789. Min Act: -0.1700
Data Index: 2902666 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4951. Min Act: -0.1700
Data Index: 8185501 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4626. Min Act: -0.1700
Data Index: 7469768 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4626. Min Act: -0.1700
Data Index: 2526136 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4626. Min Act: -0.1700
Data Index: 2938203 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4464. Min Act: -0.1700
Data Index: 5374802 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4464. Min Act: -0.1700
Data Index: 4049568 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4301. Min Act: -0.1700
Data Index: 140085 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4301. Min Act: -0.1700
Data Index: 7883683 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4301. Min Act: -0.1700
Data Index: 8606507 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4301. Min Act: -0.1700
Data Index: 280314 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5920. Min Range: -2.5920
Max Act: 2.4301. Min Act: -0.1700
Data Index: 7787973 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19