Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3585. Min Range: -6.3585
Max Act: 6.3585. Min Act: -0.1700
Data Index: 1884289 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3585. Min Range: -6.3585
Max Act: 6.2335. Min Act: -0.1700
Data Index: 1144765 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3585. Min Range: -6.3585
Max Act: 6.2022. Min Act: -0.1700
Data Index: 2127161 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3585. Min Range: -6.3585
Max Act: 6.1085. Min Act: -0.1700
Data Index: 1266445 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3585. Min Range: -6.3585
Max Act: 6.1085. Min Act: -0.1700
Data Index: 6359370 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3585. Min Range: -6.3585
Max Act: 6.0460. Min Act: -0.1700
Data Index: 5879713 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3585. Min Range: -6.3585
Max Act: 6.0460. Min Act: -0.1700
Data Index: 1054754 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3585. Min Range: -6.3585
Max Act: 6.0147. Min Act: -0.1700
Data Index: 5898444 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3585. Min Range: -6.3585
Max Act: 6.0147. Min Act: -0.1700
Data Index: 5939655 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3585. Min Range: -6.3585
Max Act: 5.9835. Min Act: -0.1700
Data Index: 3845941 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3585. Min Range: -6.3585
Max Act: 5.9522. Min Act: -0.1700
Data Index: 8419997 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3585. Min Range: -6.3585
Max Act: 5.9835. Min Act: -0.1700
Data Index: 8089646 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3585. Min Range: -6.3585
Max Act: 5.9522. Min Act: -0.1700
Data Index: 4015703 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3585. Min Range: -6.3585
Max Act: 5.9210. Min Act: -0.1700
Data Index: 5466724 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3585. Min Range: -6.3585
Max Act: 5.9210. Min Act: -0.1700
Data Index: 4921282 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3585. Min Range: -6.3585
Max Act: 5.9210. Min Act: -0.1700
Data Index: 8638953 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3585. Min Range: -6.3585
Max Act: 5.9210. Min Act: -0.1700
Data Index: 7467750 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3585. Min Range: -6.3585
Max Act: 5.8897. Min Act: -0.1700
Data Index: 6914080 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3585. Min Range: -6.3585
Max Act: 5.8897. Min Act: -0.1700
Data Index: 2239541 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3585. Min Range: -6.3585
Max Act: 5.8897. Min Act: -0.1700
Data Index: 1305132 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19