Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5482 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1209. Min Range: -6.1209
Max Act: 6.1209. Min Act: -0.1700
Data Index: 2634411 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9646. Min Act: -0.1700
Data Index: 3554850 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9334. Min Act: -0.1700
Data Index: 676938 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9334. Min Act: -0.1700
Data Index: 4309399 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.9021. Min Act: -0.1700
Data Index: 4494002 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.8709. Min Act: -0.1700
Data Index: 3752974 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.8396. Min Act: -0.1700
Data Index: 6878089 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.8084. Min Act: -0.1700
Data Index: 527554 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.8084. Min Act: -0.1700
Data Index: 6435178 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.7771. Min Act: -0.1700
Data Index: 527538 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.7771. Min Act: -0.1700
Data Index: 5100909 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.7771. Min Act: -0.1700
Data Index: 7582569 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.7771. Min Act: -0.1700
Data Index: 3601138 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.7459. Min Act: -0.1700
Data Index: 4444411 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.7459. Min Act: -0.1700
Data Index: 7023614 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.7459. Min Act: -0.1700
Data Index: 3891963 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.7459. Min Act: -0.1700
Data Index: 4246656 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.6834. Min Act: -0.1700
Data Index: 1120184 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.6834. Min Act: -0.1700
Data Index: 4136788 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1209. Min Range: -6.1209
Max Act: 5.6834. Min Act: -0.1700
Data Index: 12499 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19