Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4772 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.6968. Min Act: -0.1700
Data Index: 8827241 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.4780. Min Act: -0.1700
Data Index: 5634689 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.4780. Min Act: -0.1700
Data Index: 6708145 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.1030. Min Act: -0.1700
Data Index: 4880131 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.0718. Min Act: -0.1700
Data Index: 220668 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.1030. Min Act: -0.1700
Data Index: 2127742 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.1030. Min Act: -0.1700
Data Index: 2752834 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.1030. Min Act: -0.1700
Data Index: 5593270 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.1030. Min Act: -0.1700
Data Index: 3429326 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.1343. Min Act: -0.1700
Data Index: 8510194 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.0718. Min Act: -0.1700
Data Index: 1764508 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.0718. Min Act: -0.1700
Data Index: 6788611 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.0093. Min Act: -0.1700
Data Index: 6803857 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.0093. Min Act: -0.1700
Data Index: 4407050 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.0093. Min Act: -0.1700
Data Index: 3437047 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.0093. Min Act: -0.1700
Data Index: 8089258 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.0093. Min Act: -0.1700
Data Index: 301463 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6968. Min Range: -5.6968
Max Act: 5.0093. Min Act: -0.1700
Data Index: 6439109 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6968. Min Range: -5.6968
Max Act: 4.9780. Min Act: -0.1700
Data Index: 5986854 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6968. Min Range: -5.6968
Max Act: 4.9780. Min Act: -0.1700
Data Index: 6796170 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19