Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2669. Min Range: -6.2669
Max Act: 6.2669. Min Act: -0.1700
Data Index: 3781249 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2669. Min Range: -6.2669
Max Act: 6.0481. Min Act: -0.1700
Data Index: 2228971 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2669. Min Range: -6.2669
Max Act: 6.0169. Min Act: -0.1700
Data Index: 7678187 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2669. Min Range: -6.2669
Max Act: 6.0169. Min Act: -0.1700
Data Index: 1609964 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.9544. Min Act: -0.1700
Data Index: 3795367 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.9544. Min Act: -0.1700
Data Index: 425945 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.9544. Min Act: -0.1700
Data Index: 7749422 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.9231. Min Act: -0.1700
Data Index: 6089404 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.9231. Min Act: -0.1700
Data Index: 7469550 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.8919. Min Act: -0.1700
Data Index: 2861712 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.8919. Min Act: -0.1700
Data Index: 2297799 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.8606. Min Act: -0.1700
Data Index: 7188511 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.8294. Min Act: -0.1700
Data Index: 1529897 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.8294. Min Act: -0.1700
Data Index: 4685657 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.8294. Min Act: -0.1700
Data Index: 8082672 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.8294. Min Act: -0.1700
Data Index: 6234597 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.8294. Min Act: -0.1700
Data Index: 590931 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.7981. Min Act: -0.1700
Data Index: 412488 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.7356. Min Act: -0.1700
Data Index: 6816812 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2669. Min Range: -6.2669
Max Act: 5.7669. Min Act: -0.1700
Data Index: 5214015 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19