Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.9163. Min Act: -0.1699
Data Index: 2591547 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.9078. Min Act: -0.1700
Data Index: 8062551 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.8480. Min Act: -0.1700
Data Index: 5075571 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.8222. Min Act: -0.1700
Data Index: 3766240 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.8222. Min Act: -0.1700
Data Index: 226241 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.8137. Min Act: -0.1700
Data Index: 2788075 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.8051. Min Act: -0.1700
Data Index: 7220575 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.8051. Min Act: -0.1700
Data Index: 543253 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.8051. Min Act: -0.1700
Data Index: 5524746 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.7965. Min Act: -0.1700
Data Index: 7430806 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.7706. Min Act: -0.1700
Data Index: 3910936 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.7706. Min Act: -0.1700
Data Index: 779198 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.7620. Min Act: -0.1700
Data Index: 8138800 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.7447. Min Act: -0.1700
Data Index: 3766223 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.7620. Min Act: -0.1698
Data Index: 6461088 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.7706. Min Act: -0.1700
Data Index: 3758408 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.7620. Min Act: -0.1700
Data Index: 3969589 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.7620. Min Act: -0.1700
Data Index: 2089324 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.7620. Min Act: -0.1700
Data Index: 1503149 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9163. Min Range: -1.9163
Max Act: 1.7620. Min Act: -0.1700
Data Index: 4132534 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19