Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3171 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1464. Min Range: -5.1464
Max Act: 5.1464. Min Act: -0.1700
Data Index: 6936933 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.9589. Min Act: -0.1700
Data Index: 5076531 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.8964. Min Act: -0.1700
Data Index: 8559993 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.8964. Min Act: -0.1700
Data Index: 4675931 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.8651. Min Act: -0.1700
Data Index: 7441169 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.8651. Min Act: -0.1700
Data Index: 2036866 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.8339. Min Act: -0.1700
Data Index: 5709061 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.8026. Min Act: -0.1700
Data Index: 3271058 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.7714. Min Act: -0.1700
Data Index: 485271 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.8026. Min Act: -0.1700
Data Index: 5787046 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.7401. Min Act: -0.1700
Data Index: 7318447 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.7401. Min Act: -0.1700
Data Index: 8467903 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.7089. Min Act: -0.1700
Data Index: 4367936 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.7401. Min Act: -0.1700
Data Index: 3271050 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.7089. Min Act: -0.1700
Data Index: 3271053 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.7401. Min Act: -0.1700
Data Index: 7532836 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.7089. Min Act: -0.1700
Data Index: 5335537 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.7089. Min Act: -0.1700
Data Index: 5719000 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.6464. Min Act: -0.1700
Data Index: 1608088 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1464. Min Range: -5.1464
Max Act: 4.6776. Min Act: -0.1700
Data Index: 3470039 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19