Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 296 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3012. Min Range: -8.3012
Max Act: 8.3012. Min Act: -0.1700
Data Index: 5261981 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3012. Min Range: -8.3012
Max Act: 8.0512. Min Act: -0.1700
Data Index: 3500257 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.9887. Min Act: -0.1700
Data Index: 8116472 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.9262. Min Act: -0.1700
Data Index: 4039101 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.9262. Min Act: -0.1700
Data Index: 5244590 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.9262. Min Act: -0.1700
Data Index: 6915253 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.9262. Min Act: -0.1700
Data Index: 6291002 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.9887. Min Act: -0.1700
Data Index: 8443034 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.8324. Min Act: -0.1700
Data Index: 8021253 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.8949. Min Act: -0.1700
Data Index: 3567948 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.8324. Min Act: -0.1700
Data Index: 228542 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.7074. Min Act: -0.1700
Data Index: 1938397 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.7699. Min Act: -0.1700
Data Index: 1976866 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.7074. Min Act: -0.1700
Data Index: 3949308 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.7387. Min Act: -0.1700
Data Index: 730527 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.7699. Min Act: -0.1700
Data Index: 3384968 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.7074. Min Act: -0.1700
Data Index: 5648706 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.7699. Min Act: -0.1700
Data Index: 3721033 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.7074. Min Act: -0.1700
Data Index: 651278 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3012. Min Range: -8.3012
Max Act: 7.7074. Min Act: -0.1700
Data Index: 474292 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19