Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1258 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.9510. Min Act: -0.1700
Data Index: 3320326 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.7010. Min Act: -0.1700
Data Index: 7014050 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.6385. Min Act: -0.1700
Data Index: 6720291 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.3260. Min Act: -0.1700
Data Index: 4426932 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.3260. Min Act: -0.1700
Data Index: 2977035 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.2635. Min Act: -0.1700
Data Index: 7868555 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.2322. Min Act: -0.1700
Data Index: 6916194 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.2947. Min Act: -0.1700
Data Index: 3508756 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.2322. Min Act: -0.1700
Data Index: 3994026 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.2322. Min Act: -0.1700
Data Index: 8677910 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.2010. Min Act: -0.1700
Data Index: 6375777 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.1385. Min Act: -0.1700
Data Index: 2668809 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.1697. Min Act: -0.1700
Data Index: 1695046 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.1697. Min Act: -0.1700
Data Index: 8671610 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.1072. Min Act: -0.1700
Data Index: 1636644 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.1072. Min Act: -0.1700
Data Index: 6885273 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.1385. Min Act: -0.1700
Data Index: 145310 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.1385. Min Act: -0.1700
Data Index: 3569138 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.1385. Min Act: -0.1700
Data Index: 8385290 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9510. Min Range: -8.9510
Max Act: 8.1385. Min Act: -0.1700
Data Index: 6536857 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19