Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1634 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.9286. Min Act: -0.1700
Data Index: 4221910 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8810. Min Act: -0.1700
Data Index: 4415884 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8810. Min Act: -0.1700
Data Index: 1427511 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8652. Min Act: -0.1700
Data Index: 8590913 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8334. Min Act: -0.1700
Data Index: 160743 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8493. Min Act: -0.1700
Data Index: 1522367 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8334. Min Act: -0.1700
Data Index: 3712050 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8175. Min Act: -0.1700
Data Index: 2048171 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.7856. Min Act: -0.1700
Data Index: 2384863 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8175. Min Act: -0.1700
Data Index: 3289881 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8175. Min Act: -0.1700
Data Index: 1394343 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8175. Min Act: -0.1700
Data Index: 2305351 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8175. Min Act: -0.1700
Data Index: 3270670 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8016. Min Act: -0.1700
Data Index: 4078518 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.7856. Min Act: -0.1700
Data Index: 7472688 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.7856. Min Act: -0.1700
Data Index: 6191885 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.7537. Min Act: -0.1700
Data Index: 1622404 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.8016. Min Act: -0.1700
Data Index: 8478967 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.7537. Min Act: -0.1700
Data Index: 1405702 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9286. Min Range: -2.9286
Max Act: 2.7537. Min Act: -0.1700
Data Index: 5876095 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19