Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1122 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.3732. Min Act: -0.1700
Data Index: 5241868 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.4044. Min Act: -0.1700
Data Index: 6519204 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.3732. Min Act: -0.1700
Data Index: 4570261 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.2169. Min Act: -0.1700
Data Index: 3739493 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.1544. Min Act: -0.1700
Data Index: 4700848 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.1544. Min Act: -0.1700
Data Index: 3449241 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.1231. Min Act: -0.1700
Data Index: 3739489 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.1544. Min Act: -0.1700
Data Index: 3344331 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.1231. Min Act: -0.1700
Data Index: 8736207 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.0606. Min Act: -0.1700
Data Index: 705590 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.0919. Min Act: -0.1700
Data Index: 8767177 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.0606. Min Act: -0.1700
Data Index: 7231542 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.0919. Min Act: -0.1700
Data Index: 7231546 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.0606. Min Act: -0.1700
Data Index: 5890130 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.0919. Min Act: -0.1700
Data Index: 4600222 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.0606. Min Act: -0.1700
Data Index: 6336855 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.0606. Min Act: -0.1700
Data Index: 6421608 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.0294. Min Act: -0.1700
Data Index: 4995003 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.0919. Min Act: -0.1700
Data Index: 6821824 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4044. Min Range: -4.4044
Max Act: 4.0606. Min Act: -0.1700
Data Index: 4257193 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19