Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.8401. Min Act: -0.1700
Data Index: 8362203 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.8401. Min Act: -0.1700
Data Index: 679037 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.5589. Min Act: -0.1700
Data Index: 3011262 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.4964. Min Act: -0.1700
Data Index: 322741 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.4651. Min Act: -0.1700
Data Index: 889826 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.4651. Min Act: -0.1700
Data Index: 2110303 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.4339. Min Act: -0.1700
Data Index: 6591528 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.4651. Min Act: -0.1700
Data Index: 3209539 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.3714. Min Act: -0.1700
Data Index: 1596400 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.4026. Min Act: -0.1700
Data Index: 1964911 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.4026. Min Act: -0.1700
Data Index: 1355739 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.3714. Min Act: -0.1700
Data Index: 2303132 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.4026. Min Act: -0.1700
Data Index: 6946402 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.4026. Min Act: -0.1700
Data Index: 889821 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.3714. Min Act: -0.1700
Data Index: 7289890 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.4026. Min Act: -0.1700
Data Index: 6965477 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.3714. Min Act: -0.1700
Data Index: 8679918 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.3714. Min Act: -0.1700
Data Index: 6566164 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.3714. Min Act: -0.1700
Data Index: 7433750 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8401. Min Range: -5.8401
Max Act: 5.3401. Min Act: -0.1700
Data Index: 2198901 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19