Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1960 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3212. Min Range: -8.3212
Max Act: 8.3212. Min Act: -0.1700
Data Index: 8013660 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3212. Min Range: -8.3212
Max Act: 8.0712. Min Act: -0.1700
Data Index: 7355944 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.8837. Min Act: -0.1700
Data Index: 7968532 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.8837. Min Act: -0.1700
Data Index: 5716659 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.8212. Min Act: -0.1700
Data Index: 3745442 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.6962. Min Act: -0.1700
Data Index: 2652840 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.7587. Min Act: -0.1700
Data Index: 7718623 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.6962. Min Act: -0.1700
Data Index: 6388524 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.6962. Min Act: -0.1700
Data Index: 4130823 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.6962. Min Act: -0.1700
Data Index: 6365074 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.6337. Min Act: -0.1700
Data Index: 4513540 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.5712. Min Act: -0.1700
Data Index: 1011568 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.5712. Min Act: -0.1700
Data Index: 5227315 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.5087. Min Act: -0.1700
Data Index: 611574 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.5087. Min Act: -0.1700
Data Index: 1701659 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.5087. Min Act: -0.1700
Data Index: 4810177 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.5087. Min Act: -0.1700
Data Index: 8744444 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.4775. Min Act: -0.1700
Data Index: 2784320 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.5087. Min Act: -0.1700
Data Index: 3086568 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3212. Min Range: -8.3212
Max Act: 7.4462. Min Act: -0.1700
Data Index: 2650543 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19