Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3796 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0176. Min Range: -2.0176
Max Act: 2.0007. Min Act: -0.1700
Data Index: 1507814 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0176. Min Range: -2.0176
Max Act: 2.0176. Min Act: -0.1700
Data Index: 5601757 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9668. Min Act: -0.1700
Data Index: 2067599 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9499. Min Act: -0.1700
Data Index: 6378318 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9499. Min Act: -0.1700
Data Index: 7734678 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9499. Min Act: -0.1700
Data Index: 8738012 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9329. Min Act: -0.1700
Data Index: 3135165 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9329. Min Act: -0.1700
Data Index: 2283337 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9329. Min Act: -0.1700
Data Index: 928411 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9329. Min Act: -0.1700
Data Index: 5679081 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9158. Min Act: -0.1699
Data Index: 2168027 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9158. Min Act: -0.1700
Data Index: 8733609 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9329. Min Act: -0.1700
Data Index: 3995270 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.8988. Min Act: -0.1700
Data Index: 263837 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9158. Min Act: -0.1700
Data Index: 7863543 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9158. Min Act: -0.1700
Data Index: 6087633 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.8988. Min Act: -0.1700
Data Index: 7382892 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.8988. Min Act: -0.1700
Data Index: 7423704 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.9158. Min Act: -0.1700
Data Index: 6195879 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0176. Min Range: -2.0176
Max Act: 1.8988. Min Act: -0.1700
Data Index: 4365994 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19