Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6017 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.5569. Min Act: -0.1700
Data Index: 1645886 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.4944. Min Act: -0.1700
Data Index: 3315639 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.4319. Min Act: -0.1700
Data Index: 427169 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.3382. Min Act: -0.1700
Data Index: 2322944 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.3069. Min Act: -0.1700
Data Index: 8147171 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.3069. Min Act: -0.1700
Data Index: 5471871 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.2757. Min Act: -0.1700
Data Index: 5471870 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.2444. Min Act: -0.1700
Data Index: 11789 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.2444. Min Act: -0.1700
Data Index: 7497166 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.2132. Min Act: -0.1700
Data Index: 2960323 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.1819. Min Act: -0.1700
Data Index: 1775359 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.1819. Min Act: -0.1700
Data Index: 1469600 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.1507. Min Act: -0.1700
Data Index: 6660193 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.1194. Min Act: -0.1700
Data Index: 7827095 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.1507. Min Act: -0.1700
Data Index: 6090051 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.0882. Min Act: -0.1700
Data Index: 2326180 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.0882. Min Act: -0.1700
Data Index: 5163567 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.0569. Min Act: -0.1700
Data Index: 4593736 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.0569. Min Act: -0.1700
Data Index: 6104244 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5569. Min Range: -7.5569
Max Act: 7.0569. Min Act: -0.1700
Data Index: 2082259 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19