Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.5444. Min Act: -0.1700
Data Index: 8037646 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.4819. Min Act: -0.1700
Data Index: 1477175 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.4194. Min Act: -0.1700
Data Index: 8514222 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.4194. Min Act: -0.1700
Data Index: 683351 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.4194. Min Act: -0.1700
Data Index: 1506303 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.4194. Min Act: -0.1700
Data Index: 4657388 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.4194. Min Act: -0.1700
Data Index: 8296996 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.3569. Min Act: -0.1700
Data Index: 6723602 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.3569. Min Act: -0.1700
Data Index: 5674890 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.2319. Min Act: -0.1700
Data Index: 890066 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.1694. Min Act: -0.1700
Data Index: 1499368 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.2319. Min Act: -0.1700
Data Index: 1481112 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.2944. Min Act: -0.1700
Data Index: 1870015 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.2319. Min Act: -0.1700
Data Index: 1140742 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.2319. Min Act: -0.1700
Data Index: 2064486 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.2319. Min Act: -0.1700
Data Index: 7339296 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.1694. Min Act: -0.1700
Data Index: 1140743 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.1694. Min Act: -0.1700
Data Index: 3035836 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.1694. Min Act: -0.1700
Data Index: 6776012 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5444. Min Range: -8.5444
Max Act: 8.2319. Min Act: -0.1700
Data Index: 210620 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19