Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1582 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.8068. Min Act: -0.1700
Data Index: 3796601 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.6818. Min Act: -0.1700
Data Index: 496469 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.6818. Min Act: -0.1699
Data Index: 1974617 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.6505. Min Act: -0.1700
Data Index: 53065 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.5880. Min Act: -0.1700
Data Index: 3608727 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4943. Min Act: -0.1700
Data Index: 7185868 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.5568. Min Act: -0.1700
Data Index: 2191582 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4943. Min Act: -0.1700
Data Index: 2439151 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4630. Min Act: -0.1700
Data Index: 4447183 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4943. Min Act: -0.1700
Data Index: 7328316 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4943. Min Act: -0.1700
Data Index: 5979396 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.5255. Min Act: -0.1700
Data Index: 7236776 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4630. Min Act: -0.1700
Data Index: 90167 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4005. Min Act: -0.1700
Data Index: 1999183 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4005. Min Act: -0.1700
Data Index: 4833688 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4318. Min Act: -0.1700
Data Index: 4015394 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4318. Min Act: -0.1700
Data Index: 1974618 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4005. Min Act: -0.1700
Data Index: 8160468 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4318. Min Act: -0.1700
Data Index: 4560375 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8068. Min Range: -4.8068
Max Act: 4.4005. Min Act: -0.1700
Data Index: 5449216 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19