Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2744 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9993. Min Act: -0.1700
Data Index: 5079691 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9368. Min Act: -0.1700
Data Index: 4969402 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.8430. Min Act: -0.1700
Data Index: 5363394 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.8430. Min Act: -0.1700
Data Index: 5971219 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.8118. Min Act: -0.1700
Data Index: 5311570 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7805. Min Act: -0.1700
Data Index: 2505048 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7493. Min Act: -0.1700
Data Index: 4969367 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7493. Min Act: -0.1700
Data Index: 2792705 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7493. Min Act: -0.1700
Data Index: 4357216 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7493. Min Act: -0.1700
Data Index: 5425939 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7180. Min Act: -0.1700
Data Index: 2792713 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7180. Min Act: -0.1700
Data Index: 4969365 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7180. Min Act: -0.1700
Data Index: 2528402 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7180. Min Act: -0.1700
Data Index: 2528400 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7180. Min Act: -0.1700
Data Index: 4969377 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7180. Min Act: -0.1700
Data Index: 8268463 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6868. Min Act: -0.1700
Data Index: 5311586 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7180. Min Act: -0.1700
Data Index: 6787117 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6868. Min Act: -0.1700
Data Index: 4969399 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6868. Min Act: -0.1700
Data Index: 4969387 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19