Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.3437. Min Act: -0.1700
Data Index: 298818 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.2187. Min Act: -0.1700
Data Index: 2262356 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1874. Min Act: -0.1700
Data Index: 6473648 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.0624. Min Act: -0.1700
Data Index: 467426 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.0624. Min Act: -0.1700
Data Index: 2899638 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.0624. Min Act: -0.1700
Data Index: 8722351 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.0624. Min Act: -0.1700
Data Index: 2555274 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.0624. Min Act: -0.1700
Data Index: 1461178 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3437. Min Range: -5.3437
Max Act: 4.9999. Min Act: -0.1700
Data Index: 3959100 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.0312. Min Act: -0.1700
Data Index: 7606777 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.0312. Min Act: -0.1700
Data Index: 1941081 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.0312. Min Act: -0.1700
Data Index: 5119313 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.0312. Min Act: -0.1700
Data Index: 8708978 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3437. Min Range: -5.3437
Max Act: 4.9999. Min Act: -0.1700
Data Index: 6789381 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3437. Min Range: -5.3437
Max Act: 4.9687. Min Act: -0.1700
Data Index: 2818154 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3437. Min Range: -5.3437
Max Act: 4.9687. Min Act: -0.1700
Data Index: 4470090 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3437. Min Range: -5.3437
Max Act: 4.9687. Min Act: -0.1700
Data Index: 7331591 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3437. Min Range: -5.3437
Max Act: 4.9999. Min Act: -0.1700
Data Index: 2312967 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3437. Min Range: -5.3437
Max Act: 4.9687. Min Act: -0.1700
Data Index: 8530162 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3437. Min Range: -5.3437
Max Act: 4.9687. Min Act: -0.1700
Data Index: 3867142 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19