Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5943 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2365. Min Range: -6.2365
Max Act: 6.2365. Min Act: -0.1700
Data Index: 4832803 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2365. Min Range: -6.2365
Max Act: 6.1115. Min Act: -0.1700
Data Index: 8641033 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.9240. Min Act: -0.1700
Data Index: 5217783 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.9240. Min Act: -0.1700
Data Index: 7055364 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.8302. Min Act: -0.1700
Data Index: 5997717 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.7677. Min Act: -0.1700
Data Index: 1090003 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.7365. Min Act: -0.1700
Data Index: 3871008 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.7365. Min Act: -0.1700
Data Index: 7711007 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.7365. Min Act: -0.1700
Data Index: 705921 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.7052. Min Act: -0.1700
Data Index: 5994801 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.7052. Min Act: -0.1700
Data Index: 1545088 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.6740. Min Act: -0.1700
Data Index: 4979797 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.6427. Min Act: -0.1700
Data Index: 2388589 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.6427. Min Act: -0.1700
Data Index: 4416868 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.6427. Min Act: -0.1700
Data Index: 362130 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.6427. Min Act: -0.1700
Data Index: 8562120 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.6115. Min Act: -0.1700
Data Index: 2095993 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.6115. Min Act: -0.1700
Data Index: 8076335 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.6115. Min Act: -0.1700
Data Index: 5147902 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2365. Min Range: -6.2365
Max Act: 5.5802. Min Act: -0.1700
Data Index: 6094157 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19