Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2263 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0866. Min Range: -8.0866
Max Act: 8.0866. Min Act: -0.1700
Data Index: 732024 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0866. Min Range: -8.0866
Max Act: 8.0866. Min Act: -0.1700
Data Index: 5668561 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.7741. Min Act: -0.1700
Data Index: 2891327 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.6804. Min Act: -0.1700
Data Index: 5783041 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.6179. Min Act: -0.1700
Data Index: 1361407 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.5241. Min Act: -0.1700
Data Index: 2421738 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.6179. Min Act: -0.1700
Data Index: 4387759 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.5554. Min Act: -0.1700
Data Index: 7621470 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.5554. Min Act: -0.1700
Data Index: 4112554 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.5554. Min Act: -0.1700
Data Index: 3150201 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.5241. Min Act: -0.1700
Data Index: 961556 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.4929. Min Act: -0.1700
Data Index: 3604056 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.4304. Min Act: -0.1700
Data Index: 5653035 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.4304. Min Act: -0.1700
Data Index: 4431002 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.3991. Min Act: -0.1700
Data Index: 2775683 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.4304. Min Act: -0.1700
Data Index: 1241164 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.3991. Min Act: -0.1700
Data Index: 5300623 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.3679. Min Act: -0.1700
Data Index: 8209643 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.3366. Min Act: -0.1700
Data Index: 1259527 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0866. Min Range: -8.0866
Max Act: 7.3679. Min Act: -0.1700
Data Index: 7675015 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19