Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.7302. Min Act: -0.1700
Data Index: 8587181 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.7302. Min Act: -0.1700
Data Index: 7852225 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6676. Min Act: -0.1700
Data Index: 822217 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6676. Min Act: -0.1700
Data Index: 1631266 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6206. Min Act: -0.1700
Data Index: 6255644 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6206. Min Act: -0.1700
Data Index: 1668284 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6050. Min Act: -0.1700
Data Index: 4712476 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.5893. Min Act: -0.1700
Data Index: 1281558 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.5737. Min Act: -0.1700
Data Index: 696719 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6363. Min Act: -0.1700
Data Index: 454443 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6363. Min Act: -0.1700
Data Index: 4192242 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.5893. Min Act: -0.1700
Data Index: 6498464 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.5893. Min Act: -0.1700
Data Index: 4521486 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6363. Min Act: -0.1700
Data Index: 8347102 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6206. Min Act: -0.1700
Data Index: 4338972 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6206. Min Act: -0.1700
Data Index: 1281669 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6050. Min Act: -0.1700
Data Index: 4151963 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.6050. Min Act: -0.1700
Data Index: 7075655 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.5737. Min Act: -0.1700
Data Index: 7402054 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7302. Min Range: -3.7302
Max Act: 3.5737. Min Act: -0.1700
Data Index: 3985159 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19