Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2144 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5781. Min Act: -0.1700
Data Index: 1282189 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5781. Min Act: -0.1700
Data Index: 29281 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5781. Min Act: -0.1700
Data Index: 1077151 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5781. Min Act: -0.1700
Data Index: 2241251 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5468. Min Act: -0.1700
Data Index: 4074709 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5468. Min Act: -0.1700
Data Index: 3367811 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5468. Min Act: -0.1700
Data Index: 2960860 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5468. Min Act: -0.1700
Data Index: 7451214 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5468. Min Act: -0.1700
Data Index: 6770179 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5468. Min Act: -0.1700
Data Index: 6505248 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5468. Min Act: -0.1700
Data Index: 2401157 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5468. Min Act: -0.1700
Data Index: 2356274 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5468. Min Act: -0.1700
Data Index: 5421504 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5468. Min Act: -0.1700
Data Index: 5392736 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5468. Min Act: -0.1700
Data Index: 4484718 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5155. Min Act: -0.1700
Data Index: 72352 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5155. Min Act: -0.1700
Data Index: 2729950 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5155. Min Act: -0.1700
Data Index: 2917491 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5155. Min Act: -0.1700
Data Index: 2936271 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5781. Min Range: -3.5781
Max Act: 3.5155. Min Act: -0.1700
Data Index: 3686263 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19