Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1337 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.6242. Min Act: -0.1700
Data Index: 2934319 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.4055. Min Act: -0.1700
Data Index: 5386825 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.4055. Min Act: -0.1700
Data Index: 8202852 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.3117. Min Act: -0.1700
Data Index: 3733900 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.2805. Min Act: -0.1700
Data Index: 5271647 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.2805. Min Act: -0.1700
Data Index: 3899837 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.2180. Min Act: -0.1700
Data Index: 2895157 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.2180. Min Act: -0.1700
Data Index: 4874599 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.1242. Min Act: -0.1700
Data Index: 645656 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.1242. Min Act: -0.1700
Data Index: 3755431 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.0930. Min Act: -0.1700
Data Index: 2418146 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.0930. Min Act: -0.1700
Data Index: 7853076 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.0617. Min Act: -0.1700
Data Index: 6421851 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.0617. Min Act: -0.1700
Data Index: 2174115 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.0305. Min Act: -0.1700
Data Index: 7755590 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6242. Min Range: -7.6242
Max Act: 7.0305. Min Act: -0.1700
Data Index: 3733897 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6242. Min Range: -7.6242
Max Act: 6.9992. Min Act: -0.1700
Data Index: 2010978 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6242. Min Range: -7.6242
Max Act: 6.9992. Min Act: -0.1700
Data Index: 1547660 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6242. Min Range: -7.6242
Max Act: 6.9680. Min Act: -0.1700
Data Index: 637644 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6242. Min Range: -7.6242
Max Act: 6.9680. Min Act: -0.1700
Data Index: 3458490 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19