Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1237 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.1527. Min Act: -0.1700
Data Index: 8396115 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.1527. Min Act: -0.1700
Data Index: 4391437 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.1369. Min Act: -0.1700
Data Index: 5005422 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.1527. Min Act: -0.1700
Data Index: 3009343 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.1369. Min Act: -0.1700
Data Index: 7729860 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.1054. Min Act: -0.1700
Data Index: 6596844 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.1212. Min Act: -0.1700
Data Index: 8562705 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.1054. Min Act: -0.1700
Data Index: 315506 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.1212. Min Act: -0.1700
Data Index: 6670752 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.0897. Min Act: -0.1700
Data Index: 42450 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.0739. Min Act: -0.1700
Data Index: 5114696 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.0581. Min Act: -0.1700
Data Index: 6390554 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.0739. Min Act: -0.1700
Data Index: 7653521 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.0581. Min Act: -0.1700
Data Index: 8670900 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.0739. Min Act: -0.1700
Data Index: 6152107 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.0581. Min Act: -0.1700
Data Index: 4897842 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.0581. Min Act: -0.1700
Data Index: 2827105 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.0739. Min Act: -0.1700
Data Index: 6164529 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.0424. Min Act: -0.1700
Data Index: 2714915 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1527. Min Range: -3.1527
Max Act: 3.0739. Min Act: -0.1700
Data Index: 5955277 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19