Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4618 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5190. Min Range: -5.5190
Max Act: 5.5190. Min Act: -0.1700
Data Index: 184935 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5190. Min Range: -5.5190
Max Act: 5.3940. Min Act: -0.1700
Data Index: 2445654 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5190. Min Range: -5.5190
Max Act: 5.4253. Min Act: -0.1700
Data Index: 5818624 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5190. Min Range: -5.5190
Max Act: 5.3940. Min Act: -0.1700
Data Index: 4649407 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5190. Min Range: -5.5190
Max Act: 5.3315. Min Act: -0.1700
Data Index: 1237537 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5190. Min Range: -5.5190
Max Act: 5.3315. Min Act: -0.1700
Data Index: 6179489 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5190. Min Range: -5.5190
Max Act: 5.1128. Min Act: -0.1700
Data Index: 8587881 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5190. Min Range: -5.5190
Max Act: 5.1128. Min Act: -0.1700
Data Index: 2588003 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5190. Min Range: -5.5190
Max Act: 5.0503. Min Act: -0.1700
Data Index: 4780395 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5190. Min Range: -5.5190
Max Act: 5.0815. Min Act: -0.1700
Data Index: 6540471 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5190. Min Range: -5.5190
Max Act: 4.9878. Min Act: -0.1700
Data Index: 5399536 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5190. Min Range: -5.5190
Max Act: 5.0190. Min Act: -0.1700
Data Index: 5600904 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5190. Min Range: -5.5190
Max Act: 4.9878. Min Act: -0.1700
Data Index: 6103092 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5190. Min Range: -5.5190
Max Act: 4.9878. Min Act: -0.1700
Data Index: 1522419 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5190. Min Range: -5.5190
Max Act: 4.9565. Min Act: -0.1700
Data Index: 1721711 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5190. Min Range: -5.5190
Max Act: 4.9253. Min Act: -0.1700
Data Index: 685028 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5190. Min Range: -5.5190
Max Act: 4.9565. Min Act: -0.1700
Data Index: 690372 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5190. Min Range: -5.5190
Max Act: 4.9565. Min Act: -0.1700
Data Index: 2480718 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5190. Min Range: -5.5190
Max Act: 4.9565. Min Act: -0.1700
Data Index: 6529805 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5190. Min Range: -5.5190
Max Act: 4.9565. Min Act: -0.1700
Data Index: 3270645 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19