Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 235 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0269. Min Range: -7.0269
Max Act: 7.0269. Min Act: -0.1700
Data Index: 5287586 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.9957. Min Act: -0.1700
Data Index: 3777513 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.9332. Min Act: -0.1700
Data Index: 658068 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.9019. Min Act: -0.1700
Data Index: 7113370 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.8394. Min Act: -0.1700
Data Index: 8755723 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.8394. Min Act: -0.1700
Data Index: 4369525 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.7769. Min Act: -0.1700
Data Index: 3428759 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.7457. Min Act: -0.1700
Data Index: 4095961 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.7144. Min Act: -0.1700
Data Index: 6195876 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.7144. Min Act: -0.1700
Data Index: 2069216 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.6519. Min Act: -0.1700
Data Index: 6224642 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.6832. Min Act: -0.1700
Data Index: 7074668 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.6207. Min Act: -0.1700
Data Index: 3844003 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.5582. Min Act: -0.1700
Data Index: 5911975 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.5582. Min Act: -0.1700
Data Index: 6181163 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.5582. Min Act: -0.1700
Data Index: 2682030 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.5269. Min Act: -0.1700
Data Index: 2794225 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.4957. Min Act: -0.1700
Data Index: 3604569 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.4644. Min Act: -0.1700
Data Index: 4251218 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0269. Min Range: -7.0269
Max Act: 6.4332. Min Act: -0.1700
Data Index: 1553248 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19