Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.2281. Min Act: -0.1700
Data Index: 4272458 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0094. Min Act: -0.1700
Data Index: 2941968 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2281. Min Range: -5.2281
Max Act: 5.0094. Min Act: -0.1700
Data Index: 236317 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.9469. Min Act: -0.1700
Data Index: 3947899 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8844. Min Act: -0.1700
Data Index: 4994602 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8844. Min Act: -0.1700
Data Index: 8262720 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8844. Min Act: -0.1700
Data Index: 1887974 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8844. Min Act: -0.1700
Data Index: 3497059 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8844. Min Act: -0.1700
Data Index: 3540426 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8531. Min Act: -0.1700
Data Index: 2932522 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8531. Min Act: -0.1700
Data Index: 2460175 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8219. Min Act: -0.1700
Data Index: 5598694 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8219. Min Act: -0.1700
Data Index: 657585 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8219. Min Act: -0.1700
Data Index: 1705557 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8219. Min Act: -0.1700
Data Index: 8690164 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.8219. Min Act: -0.1700
Data Index: 1155105 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.7906. Min Act: -0.1700
Data Index: 249292 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.7906. Min Act: -0.1700
Data Index: 5766058 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.7906. Min Act: -0.1700
Data Index: 1152607 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2281. Min Range: -5.2281
Max Act: 4.7594. Min Act: -0.1700
Data Index: 2081210 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19