Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 373 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.9213. Min Act: -0.1700
Data Index: 3170697 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.7338. Min Act: -0.1700
Data Index: 3008138 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.7650. Min Act: -0.1700
Data Index: 2195307 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.7025. Min Act: -0.1700
Data Index: 605751 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.6713. Min Act: -0.1700
Data Index: 5118328 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.5775. Min Act: -0.1700
Data Index: 2341955 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.5775. Min Act: -0.1700
Data Index: 3771605 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.5463. Min Act: -0.1700
Data Index: 2235587 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.5150. Min Act: -0.1700
Data Index: 6077120 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.5150. Min Act: -0.1700
Data Index: 3093790 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.5463. Min Act: -0.1700
Data Index: 578404 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.4838. Min Act: -0.1700
Data Index: 7265992 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.4838. Min Act: -0.1700
Data Index: 3280329 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.4838. Min Act: -0.1700
Data Index: 1607208 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.4838. Min Act: -0.1700
Data Index: 4602339 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.4525. Min Act: -0.1700
Data Index: 5498274 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.4525. Min Act: -0.1700
Data Index: 3066568 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.3900. Min Act: -0.1700
Data Index: 5362736 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.4213. Min Act: -0.1700
Data Index: 5277560 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9213. Min Range: -6.9213
Max Act: 6.3900. Min Act: -0.1700
Data Index: 2388053 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19