Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1283 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.4435. Min Act: -0.1700
Data Index: 1474344 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.3185. Min Act: -0.1700
Data Index: 1008258 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.1935. Min Act: -0.1700
Data Index: 8734465 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.1935. Min Act: -0.1700
Data Index: 7796671 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.1310. Min Act: -0.1700
Data Index: 2925893 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.1310. Min Act: -0.1700
Data Index: 3269126 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.0998. Min Act: -0.1700
Data Index: 3474207 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.0685. Min Act: -0.1700
Data Index: 2813805 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.0685. Min Act: -0.1700
Data Index: 8774449 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.0685. Min Act: -0.1700
Data Index: 586259 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.0373. Min Act: -0.1700
Data Index: 1675471 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.0060. Min Act: -0.1700
Data Index: 8528293 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.0060. Min Act: -0.1700
Data Index: 6611203 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4435. Min Range: -8.4435
Max Act: 8.0060. Min Act: -0.1700
Data Index: 1802307 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4435. Min Range: -8.4435
Max Act: 7.9748. Min Act: -0.1700
Data Index: 6233088 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4435. Min Range: -8.4435
Max Act: 7.9435. Min Act: -0.1700
Data Index: 784532 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4435. Min Range: -8.4435
Max Act: 7.9748. Min Act: -0.1700
Data Index: 4256943 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4435. Min Range: -8.4435
Max Act: 7.9748. Min Act: -0.1700
Data Index: 7788993 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4435. Min Range: -8.4435
Max Act: 7.9748. Min Act: -0.1700
Data Index: 5987123 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4435. Min Range: -8.4435
Max Act: 7.9748. Min Act: -0.1700
Data Index: 8092808 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19