Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2316 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.8741. Min Act: -0.1700
Data Index: 3266640 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.8116. Min Act: -0.1700
Data Index: 8692273 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.7491. Min Act: -0.1700
Data Index: 3991429 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.6241. Min Act: -0.1700
Data Index: 8119907 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.5929. Min Act: -0.1700
Data Index: 3641905 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.4991. Min Act: -0.1700
Data Index: 8004830 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.4054. Min Act: -0.1700
Data Index: 4188200 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.3741. Min Act: -0.1700
Data Index: 3648771 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.3116. Min Act: -0.1700
Data Index: 5695560 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.2804. Min Act: -0.1700
Data Index: 8410832 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.2491. Min Act: -0.1700
Data Index: 7752995 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.2804. Min Act: -0.1700
Data Index: 4981109 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.2491. Min Act: -0.1700
Data Index: 2953145 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.2491. Min Act: -0.1700
Data Index: 989672 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.1866. Min Act: -0.1700
Data Index: 2821157 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.1554. Min Act: -0.1700
Data Index: 7195882 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.1554. Min Act: -0.1700
Data Index: 8043465 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.1241. Min Act: -0.1700
Data Index: 1381469 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.1241. Min Act: -0.1700
Data Index: 3639638 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8741. Min Range: -7.8741
Max Act: 7.1241. Min Act: -0.1700
Data Index: 6791757 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19