Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6002 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.6283. Min Act: -0.1700
Data Index: 8534390 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.5033. Min Act: -0.1700
Data Index: 5117702 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.5658. Min Act: -0.1700
Data Index: 3469197 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.3158. Min Act: -0.1700
Data Index: 6907705 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.3158. Min Act: -0.1700
Data Index: 8799196 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.2533. Min Act: -0.1700
Data Index: 1451102 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.1908. Min Act: -0.1700
Data Index: 3932189 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.1283. Min Act: -0.1700
Data Index: 5079757 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.1283. Min Act: -0.1700
Data Index: 269083 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.0658. Min Act: -0.1700
Data Index: 4007108 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.0658. Min Act: -0.1700
Data Index: 4064059 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.0658. Min Act: -0.1700
Data Index: 6401711 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.0658. Min Act: -0.1700
Data Index: 5468424 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.0658. Min Act: -0.1700
Data Index: 2675676 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.0658. Min Act: -0.1700
Data Index: 5628749 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.0033. Min Act: -0.1700
Data Index: 40012 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.0033. Min Act: -0.1700
Data Index: 3700727 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.0033. Min Act: -0.1700
Data Index: 2562064 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.0033. Min Act: -0.1700
Data Index: 7778282 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6283. Min Range: -8.6283
Max Act: 8.0033. Min Act: -0.1700
Data Index: 8783788 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19