Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3494 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.6713. Min Act: -0.1700
Data Index: 7262563 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.6088. Min Act: -0.1700
Data Index: 3546166 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.5151. Min Act: -0.1700
Data Index: 2890783 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.4838. Min Act: -0.1700
Data Index: 6930933 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.4213. Min Act: -0.1700
Data Index: 6197626 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.3900. Min Act: -0.1700
Data Index: 4412150 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.3900. Min Act: -0.1700
Data Index: 1658246 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.3588. Min Act: -0.1700
Data Index: 7529863 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.3588. Min Act: -0.1700
Data Index: 2644713 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.3588. Min Act: -0.1700
Data Index: 7753171 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.3588. Min Act: -0.1700
Data Index: 3588942 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.3275. Min Act: -0.1700
Data Index: 5812975 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.3275. Min Act: -0.1700
Data Index: 2217056 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.2963. Min Act: -0.1700
Data Index: 3868905 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.2650. Min Act: -0.1700
Data Index: 472385 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.2650. Min Act: -0.1700
Data Index: 8614320 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.2650. Min Act: -0.1700
Data Index: 1951330 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.2650. Min Act: -0.1700
Data Index: 7474428 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.2650. Min Act: -0.1700
Data Index: 5547061 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6713. Min Range: -4.6713
Max Act: 4.2338. Min Act: -0.1700
Data Index: 1964646 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19