Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1769 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0419. Min Range: -7.0419
Max Act: 7.0419. Min Act: -0.1646
Data Index: 6403044 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.8544. Min Act: -0.1700
Data Index: 7260046 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.5419. Min Act: -0.1700
Data Index: 4413101 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.5107. Min Act: -0.1678
Data Index: 8311294 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.5107. Min Act: -0.1700
Data Index: 5704411 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.4482. Min Act: -0.1699
Data Index: 1096540 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.3857. Min Act: -0.1700
Data Index: 4439272 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.3232. Min Act: -0.1700
Data Index: 2269342 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.2919. Min Act: -0.1700
Data Index: 6676932 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.2919. Min Act: -0.1700
Data Index: 3202782 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.2607. Min Act: -0.1700
Data Index: 8492832 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.2294. Min Act: -0.1700
Data Index: 7708485 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.2294. Min Act: -0.1700
Data Index: 7341805 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.2294. Min Act: -0.1700
Data Index: 5405830 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.1982. Min Act: -0.1700
Data Index: 7974914 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.1669. Min Act: -0.1700
Data Index: 5936388 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.1357. Min Act: -0.1700
Data Index: 6598470 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.1357. Min Act: -0.1700
Data Index: 4984394 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.1357. Min Act: -0.1700
Data Index: 114896 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0419. Min Range: -7.0419
Max Act: 6.0732. Min Act: -0.1691
Data Index: 5827293 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19