Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0514. Min Range: -3.0514
Max Act: 3.0514. Min Act: -0.1700
Data Index: 4706869 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.9883. Min Act: -0.1700
Data Index: 429409 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.9091. Min Act: -0.1700
Data Index: 8487617 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.9091. Min Act: -0.1700
Data Index: 4365264 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.8774. Min Act: -0.1700
Data Index: 4706868 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.8297. Min Act: -0.1700
Data Index: 7799009 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.8615. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.8138. Min Act: -0.1700
Data Index: 657239 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7820. Min Act: -0.1700
Data Index: 7807619 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7660. Min Act: -0.1700
Data Index: 4044598 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7979. Min Act: -0.1700
Data Index: 6537920 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7660. Min Act: -0.1700
Data Index: 667041 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7660. Min Act: -0.1700
Data Index: 4748119 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7820. Min Act: -0.1700
Data Index: 8315695 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7501. Min Act: -0.1700
Data Index: 6770450 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7660. Min Act: -0.1700
Data Index: 5625381 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7660. Min Act: -0.1700
Data Index: 7575369 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7660. Min Act: -0.1700
Data Index: 1630143 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7660. Min Act: -0.1700
Data Index: 7314301 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0514. Min Range: -3.0514
Max Act: 2.7660. Min Act: -0.1700
Data Index: 3116056 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19