Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5467 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.6864. Min Act: -0.1700
Data Index: 6079352 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.6864. Min Act: -0.1700
Data Index: 3229248 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.6239. Min Act: -0.1700
Data Index: 1910167 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.5614. Min Act: -0.1700
Data Index: 3950564 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.4364. Min Act: -0.1700
Data Index: 3699730 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.4364. Min Act: -0.1700
Data Index: 8775493 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.3739. Min Act: -0.1700
Data Index: 8730398 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.3739. Min Act: -0.1700
Data Index: 7734406 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.3114. Min Act: -0.1700
Data Index: 1363732 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.3114. Min Act: -0.1700
Data Index: 8502131 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.2489. Min Act: -0.1700
Data Index: 4591906 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.2489. Min Act: -0.1700
Data Index: 6079070 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.2489. Min Act: -0.1700
Data Index: 244215 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.1864. Min Act: -0.1700
Data Index: 8214806 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.1864. Min Act: -0.1700
Data Index: 3791803 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.2489. Min Act: -0.1700
Data Index: 8528869 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.1239. Min Act: -0.1700
Data Index: 1726869 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.1239. Min Act: -0.1700
Data Index: 3083634 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.1239. Min Act: -0.1700
Data Index: 8041249 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6864. Min Range: -8.6864
Max Act: 8.0614. Min Act: -0.1700
Data Index: 4268005 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19