Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.3554. Min Act: -0.1700
Data Index: 44819 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.2929. Min Act: -0.1700
Data Index: 400850 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.2929. Min Act: -0.1700
Data Index: 886710 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.2929. Min Act: -0.1700
Data Index: 892354 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.2616. Min Act: -0.1700
Data Index: 6569539 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.2304. Min Act: -0.1700
Data Index: 2900354 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.2304. Min Act: -0.1700
Data Index: 674710 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.2304. Min Act: -0.1700
Data Index: 5020374 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.1991. Min Act: -0.1700
Data Index: 7083089 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.1679. Min Act: -0.1700
Data Index: 2900353 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.1679. Min Act: -0.1700
Data Index: 1213371 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.1366. Min Act: -0.1700
Data Index: 674711 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.1054. Min Act: -0.1700
Data Index: 4821528 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.1366. Min Act: -0.1700
Data Index: 6534859 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.1366. Min Act: -0.1700
Data Index: 674709 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.1054. Min Act: -0.1700
Data Index: 1076242 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.1054. Min Act: -0.1700
Data Index: 6358971 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.1054. Min Act: -0.1700
Data Index: 2233143 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.0741. Min Act: -0.1700
Data Index: 2260051 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3554. Min Range: -5.3554
Max Act: 5.0741. Min Act: -0.1700
Data Index: 2287049 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19