Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.4665. Min Act: -0.1699
Data Index: 7661967 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.4137. Min Act: -0.1699
Data Index: 8495045 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.3784. Min Act: -0.1679
Data Index: 6450537 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.3608. Min Act: -0.1685
Data Index: 568139 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.3608. Min Act: -0.1699
Data Index: 2666636 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.3608. Min Act: -0.1700
Data Index: 5813162 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.3432. Min Act: -0.1698
Data Index: 3108787 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.3079. Min Act: -0.1698
Data Index: 1453900 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.3079. Min Act: -0.1696
Data Index: 5813326 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.3079. Min Act: -0.1700
Data Index: 7222744 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.3079. Min Act: -0.1700
Data Index: 4905058 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.3255. Min Act: -0.1686
Data Index: 1464283 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.3079. Min Act: -0.1693
Data Index: 5457892 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.2903. Min Act: -0.1700
Data Index: 6197307 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.2903. Min Act: -0.1631
Data Index: 5577336 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.2903. Min Act: -0.1699
Data Index: 1373625 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.2903. Min Act: -0.1691
Data Index: 333405 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.2550. Min Act: -0.1699
Data Index: 3830738 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.2726. Min Act: -0.1700
Data Index: 1271008 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4665. Min Range: -1.4665
Max Act: 1.2726. Min Act: -0.1691
Data Index: 3906976 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19