Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 972 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3424. Min Range: -7.3424
Max Act: 7.3424. Min Act: -0.1700
Data Index: 1281668 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3424. Min Range: -7.3424
Max Act: 7.1862. Min Act: -0.1700
Data Index: 6882049 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.9987. Min Act: -0.1700
Data Index: 6168852 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.9674. Min Act: -0.1700
Data Index: 3834778 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.9362. Min Act: -0.1700
Data Index: 4304444 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.9362. Min Act: -0.1700
Data Index: 6523057 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.9049. Min Act: -0.1700
Data Index: 837620 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.9049. Min Act: -0.1700
Data Index: 116291 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.8737. Min Act: -0.1700
Data Index: 1802706 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.8424. Min Act: -0.1700
Data Index: 1344535 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.8112. Min Act: -0.1700
Data Index: 5314219 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.8112. Min Act: -0.1700
Data Index: 1058137 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.8112. Min Act: -0.1700
Data Index: 6422402 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.7487. Min Act: -0.1700
Data Index: 3844371 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.7799. Min Act: -0.1700
Data Index: 434717 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.7487. Min Act: -0.1700
Data Index: 8450214 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.7799. Min Act: -0.1700
Data Index: 3682193 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.7487. Min Act: -0.1700
Data Index: 5752584 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.7174. Min Act: -0.1700
Data Index: 8490334 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3424. Min Range: -7.3424
Max Act: 6.6862. Min Act: -0.1700
Data Index: 2093658 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19