Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3238 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.8224. Min Act: -0.1700
Data Index: 7020905 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.6036. Min Act: -0.1700
Data Index: 5763843 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.5724. Min Act: -0.1700
Data Index: 1372534 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.5411. Min Act: -0.1700
Data Index: 6209158 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.5099. Min Act: -0.1700
Data Index: 7520368 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.4786. Min Act: -0.1700
Data Index: 5918221 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.4161. Min Act: -0.1700
Data Index: 5982360 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.3536. Min Act: -0.1700
Data Index: 1716231 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.2911. Min Act: -0.1700
Data Index: 2794102 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.3224. Min Act: -0.1700
Data Index: 1201002 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.3536. Min Act: -0.1700
Data Index: 7401814 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.2911. Min Act: -0.1700
Data Index: 2253576 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.2911. Min Act: -0.1700
Data Index: 5692608 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.2911. Min Act: -0.1700
Data Index: 2854080 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.2599. Min Act: -0.1700
Data Index: 8455686 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.2599. Min Act: -0.1700
Data Index: 6627115 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.2599. Min Act: -0.1700
Data Index: 4157719 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.2286. Min Act: -0.1700
Data Index: 8002955 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.2286. Min Act: -0.1700
Data Index: 1008148 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8224. Min Range: -7.8224
Max Act: 7.2286. Min Act: -0.1700
Data Index: 463818 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19