Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4731 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.6791. Min Act: -0.1700
Data Index: 1649932 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.4604. Min Act: -0.1700
Data Index: 3210476 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.3979. Min Act: -0.1700
Data Index: 4374259 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.3354. Min Act: -0.1699
Data Index: 7333476 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.3354. Min Act: -0.1700
Data Index: 2027227 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.3354. Min Act: -0.1700
Data Index: 7413382 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.3041. Min Act: -0.1700
Data Index: 5852569 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.3041. Min Act: -0.1700
Data Index: 4803768 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2729. Min Act: -0.1700
Data Index: 8590846 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2729. Min Act: -0.1700
Data Index: 6995102 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2729. Min Act: -0.1700
Data Index: 2850608 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2729. Min Act: -0.1700
Data Index: 8432059 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2729. Min Act: -0.1700
Data Index: 7413381 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2416. Min Act: -0.1700
Data Index: 4053229 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2416. Min Act: -0.1700
Data Index: 2405049 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2416. Min Act: -0.1700
Data Index: 8379144 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2104. Min Act: -0.1700
Data Index: 6027014 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2416. Min Act: -0.1700
Data Index: 4055725 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2416. Min Act: -0.1699
Data Index: 1245246 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6791. Min Range: -5.6791
Max Act: 5.2416. Min Act: -0.1700
Data Index: 6719277 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19