Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0952. Min Range: -5.0952
Max Act: 5.0952. Min Act: -0.1700
Data Index: 4382161 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.9077. Min Act: -0.1700
Data Index: 1764024 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.8765. Min Act: -0.1700
Data Index: 4533749 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.8452. Min Act: -0.1700
Data Index: 5076143 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.7202. Min Act: -0.1700
Data Index: 1124025 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.6265. Min Act: -0.1700
Data Index: 894873 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.6265. Min Act: -0.1700
Data Index: 1133803 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.5952. Min Act: -0.1700
Data Index: 1541749 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.5952. Min Act: -0.1700
Data Index: 2764208 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.5952. Min Act: -0.1700
Data Index: 1449741 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.5640. Min Act: -0.1700
Data Index: 1842486 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.5327. Min Act: -0.1700
Data Index: 1797023 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.5015. Min Act: -0.1700
Data Index: 6528860 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.5015. Min Act: -0.1700
Data Index: 1054644 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.5015. Min Act: -0.1700
Data Index: 999531 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.5015. Min Act: -0.1700
Data Index: 4126683 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.5015. Min Act: -0.1700
Data Index: 1517664 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.4702. Min Act: -0.1700
Data Index: 3033605 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.4390. Min Act: -0.1700
Data Index: 2861548 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0952. Min Range: -5.0952
Max Act: 4.4390. Min Act: -0.1700
Data Index: 2291963 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19