Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3174 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.6948. Min Act: -0.1700
Data Index: 6765292 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.6323. Min Act: -0.1700
Data Index: 1581419 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.6323. Min Act: -0.1700
Data Index: 6451000 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.6323. Min Act: -0.1700
Data Index: 1092095 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.6323. Min Act: -0.1700
Data Index: 8786071 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.6011. Min Act: -0.1700
Data Index: 736882 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.6011. Min Act: -0.1700
Data Index: 5009929 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.4448. Min Act: -0.1700
Data Index: 2563722 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.4761. Min Act: -0.1700
Data Index: 6749181 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.4448. Min Act: -0.1700
Data Index: 5808054 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.4448. Min Act: -0.1700
Data Index: 2256007 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.4448. Min Act: -0.1700
Data Index: 1569539 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.4136. Min Act: -0.1700
Data Index: 4032035 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.3823. Min Act: -0.1700
Data Index: 269389 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.4136. Min Act: -0.1700
Data Index: 5820821 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.4136. Min Act: -0.1700
Data Index: 1442763 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.4136. Min Act: -0.1700
Data Index: 1664385 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.4448. Min Act: -0.1700
Data Index: 3523259 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.3823. Min Act: -0.1700
Data Index: 8107477 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6948. Min Range: -5.6948
Max Act: 5.3511. Min Act: -0.1700
Data Index: 8184403 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19