Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.6881. Min Act: -0.1700
Data Index: 3598700 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.5006. Min Act: -0.1700
Data Index: 3011698 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.4068. Min Act: -0.1700
Data Index: 8257614 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.3756. Min Act: -0.1700
Data Index: 8326059 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.3443. Min Act: -0.1700
Data Index: 6059153 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.3131. Min Act: -0.1700
Data Index: 2415206 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.2818. Min Act: -0.1700
Data Index: 1019199 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.2818. Min Act: -0.1700
Data Index: 4051016 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.2506. Min Act: -0.1700
Data Index: 3710767 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.2193. Min Act: -0.1700
Data Index: 6737651 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.1568. Min Act: -0.1700
Data Index: 2522225 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.1881. Min Act: -0.1700
Data Index: 5566806 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.0631. Min Act: -0.1700
Data Index: 7433753 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.0943. Min Act: -0.1700
Data Index: 3589146 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.0943. Min Act: -0.1700
Data Index: 2311207 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.0631. Min Act: -0.1700
Data Index: 7514469 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.0631. Min Act: -0.1700
Data Index: 7827434 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.0318. Min Act: -0.1700
Data Index: 6464946 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.0631. Min Act: -0.1700
Data Index: 6485122 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6881. Min Range: -7.6881
Max Act: 7.0318. Min Act: -0.1700
Data Index: 2585064 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19