Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2813 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.8685. Min Act: -0.1700
Data Index: 7023261 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.6185. Min Act: -0.1700
Data Index: 7185355 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.4935. Min Act: -0.1700
Data Index: 7238662 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.4935. Min Act: -0.1700
Data Index: 4397430 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.4935. Min Act: -0.1700
Data Index: 4397435 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.4623. Min Act: -0.1700
Data Index: 3281629 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.4310. Min Act: -0.1700
Data Index: 3281626 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.4310. Min Act: -0.1700
Data Index: 1730224 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.3998. Min Act: -0.1700
Data Index: 8035560 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.3685. Min Act: -0.1700
Data Index: 1807605 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.3373. Min Act: -0.1700
Data Index: 8606401 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.3685. Min Act: -0.1700
Data Index: 856035 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.3060. Min Act: -0.1700
Data Index: 4472649 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.3373. Min Act: -0.1700
Data Index: 2189957 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.3373. Min Act: -0.1700
Data Index: 2872380 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.3060. Min Act: -0.1700
Data Index: 1643578 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.3060. Min Act: -0.1700
Data Index: 6283781 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.3060. Min Act: -0.1700
Data Index: 4098202 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.2748. Min Act: -0.1700
Data Index: 50561 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8685. Min Range: -4.8685
Max Act: 4.3060. Min Act: -0.1700
Data Index: 7085097 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19