Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.3615. Min Act: -0.1700
Data Index: 3479102 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.3287. Min Act: -0.1700
Data Index: 5682944 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.3451. Min Act: -0.1700
Data Index: 8513791 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.3123. Min Act: -0.1700
Data Index: 1396345 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2794. Min Act: -0.1700
Data Index: 765120 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2629. Min Act: -0.1700
Data Index: 3921204 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2959. Min Act: -0.1700
Data Index: 3492706 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2629. Min Act: -0.1700
Data Index: 1682048 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2464. Min Act: -0.1700
Data Index: 4938983 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2794. Min Act: -0.1700
Data Index: 168875 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2629. Min Act: -0.1700
Data Index: 1046936 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2629. Min Act: -0.1700
Data Index: 7882650 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2629. Min Act: -0.1700
Data Index: 3080784 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2629. Min Act: -0.1700
Data Index: 3201495 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2299. Min Act: -0.1700
Data Index: 4606233 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2629. Min Act: -0.1700
Data Index: 7882649 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2464. Min Act: -0.1700
Data Index: 5486119 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2464. Min Act: -0.1700
Data Index: 2160905 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2464. Min Act: -0.1700
Data Index: 7740408 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3615. Min Range: -2.3615
Max Act: 2.2464. Min Act: -0.1700
Data Index: 1166045 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19