Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4633 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0045. Min Range: -7.0045
Max Act: 7.0045. Min Act: -0.1700
Data Index: 6266352 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.9108. Min Act: -0.1700
Data Index: 1906311 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.9108. Min Act: -0.1700
Data Index: 2783397 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.7545. Min Act: -0.1700
Data Index: 2114317 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.7545. Min Act: -0.1700
Data Index: 1552134 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.7545. Min Act: -0.1700
Data Index: 3765196 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.7545. Min Act: -0.1700
Data Index: 923540 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.7233. Min Act: -0.1700
Data Index: 3301254 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.6920. Min Act: -0.1700
Data Index: 1560362 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.6608. Min Act: -0.1700
Data Index: 5599280 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.6295. Min Act: -0.1700
Data Index: 979534 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.5983. Min Act: -0.1700
Data Index: 1951769 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.5670. Min Act: -0.1700
Data Index: 7867962 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.5983. Min Act: -0.1700
Data Index: 910543 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.5670. Min Act: -0.1700
Data Index: 1514182 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.5670. Min Act: -0.1700
Data Index: 5875795 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.5358. Min Act: -0.1700
Data Index: 8768535 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.5358. Min Act: -0.1700
Data Index: 5453316 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.4733. Min Act: -0.1700
Data Index: 7025862 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.4733. Min Act: -0.1700
Data Index: 1428748 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19