Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1919 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.7481. Min Act: -0.1700
Data Index: 6469559 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.5293. Min Act: -0.1700
Data Index: 5727457 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.2168. Min Act: -0.1700
Data Index: 1095574 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.1543. Min Act: -0.1700
Data Index: 6849019 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.1231. Min Act: -0.1700
Data Index: 6702574 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.1543. Min Act: -0.1700
Data Index: 8583318 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.1231. Min Act: -0.1700
Data Index: 5265349 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.1231. Min Act: -0.1700
Data Index: 1870413 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.0918. Min Act: -0.1700
Data Index: 3495850 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.0918. Min Act: -0.1700
Data Index: 2215827 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.0606. Min Act: -0.1700
Data Index: 5399463 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.0606. Min Act: -0.1700
Data Index: 6701452 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.0606. Min Act: -0.1700
Data Index: 7108342 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.0293. Min Act: -0.1700
Data Index: 3200904 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.0293. Min Act: -0.1700
Data Index: 1696122 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7481. Min Range: -5.7481
Max Act: 5.0293. Min Act: -0.1700
Data Index: 2769924 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7481. Min Range: -5.7481
Max Act: 4.9981. Min Act: -0.1700
Data Index: 2297056 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7481. Min Range: -5.7481
Max Act: 4.9981. Min Act: -0.1700
Data Index: 3810984 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7481. Min Range: -5.7481
Max Act: 4.9981. Min Act: -0.1700
Data Index: 4240574 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7481. Min Range: -5.7481
Max Act: 4.9668. Min Act: -0.1700
Data Index: 273029 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19