Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.6187. Min Act: -0.1700
Data Index: 5372337 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.4624. Min Act: -0.1700
Data Index: 2635184 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.4937. Min Act: -0.1700
Data Index: 2094680 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.4312. Min Act: -0.1700
Data Index: 1113627 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.3374. Min Act: -0.1700
Data Index: 3546420 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.3999. Min Act: -0.1700
Data Index: 4801086 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.3374. Min Act: -0.1700
Data Index: 6603448 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.3374. Min Act: -0.1700
Data Index: 4273385 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.3687. Min Act: -0.1700
Data Index: 218363 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.3687. Min Act: -0.1700
Data Index: 258612 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.4312. Min Act: -0.1700
Data Index: 6873033 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.3374. Min Act: -0.1700
Data Index: 5366501 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.3062. Min Act: -0.1700
Data Index: 4010068 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.3062. Min Act: -0.1700
Data Index: 545036 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.2749. Min Act: -0.1700
Data Index: 6683342 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.2749. Min Act: -0.1700
Data Index: 433338 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.2437. Min Act: -0.1700
Data Index: 83357 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.2749. Min Act: -0.1700
Data Index: 1537785 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.2437. Min Act: -0.1700
Data Index: 4146364 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6187. Min Range: -4.6187
Max Act: 4.2437. Min Act: -0.1700
Data Index: 5544424 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19