Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1070 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.6065. Min Act: -0.1700
Data Index: 4593788 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.5453. Min Act: -0.1700
Data Index: 8414647 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.5278. Min Act: -0.1700
Data Index: 4376156 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.5366. Min Act: -0.1700
Data Index: 4716423 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.5190. Min Act: -0.1700
Data Index: 7839658 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.5015. Min Act: -0.1700
Data Index: 7618832 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4927. Min Act: -0.1700
Data Index: 1714021 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.5015. Min Act: -0.1700
Data Index: 8001652 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4839. Min Act: -0.1700
Data Index: 4376157 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4663. Min Act: -0.1700
Data Index: 8447388 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4839. Min Act: -0.1700
Data Index: 2472730 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4839. Min Act: -0.1700
Data Index: 2974356 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4575. Min Act: -0.1700
Data Index: 2365620 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4575. Min Act: -0.1700
Data Index: 3917265 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4487. Min Act: -0.1700
Data Index: 8812627 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4575. Min Act: -0.1700
Data Index: 7039489 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4487. Min Act: -0.1700
Data Index: 8654937 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4311. Min Act: -0.1700
Data Index: 2654977 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4311. Min Act: -0.1700
Data Index: 8313711 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6065. Min Range: -1.6065
Max Act: 1.4399. Min Act: -0.1700
Data Index: 1698645 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19