Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 74 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.5817. Min Act: -0.1700
Data Index: 3166497 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.5505. Min Act: -0.1700
Data Index: 5306403 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.5505. Min Act: -0.1700
Data Index: 5092983 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.4880. Min Act: -0.1700
Data Index: 4041733 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.4880. Min Act: -0.1700
Data Index: 3457682 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.3942. Min Act: -0.1700
Data Index: 3248619 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.3942. Min Act: -0.1700
Data Index: 1341441 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.3942. Min Act: -0.1700
Data Index: 5101628 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.3630. Min Act: -0.1700
Data Index: 2489982 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.3317. Min Act: -0.1700
Data Index: 4504114 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.3630. Min Act: -0.1700
Data Index: 6215493 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.3005. Min Act: -0.1700
Data Index: 3067277 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.3005. Min Act: -0.1700
Data Index: 8643090 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.2380. Min Act: -0.1700
Data Index: 7952434 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.2380. Min Act: -0.1700
Data Index: 7284075 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.2380. Min Act: -0.1700
Data Index: 3322870 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.2067. Min Act: -0.1700
Data Index: 1381094 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.2380. Min Act: -0.1700
Data Index: 1123339 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.2067. Min Act: -0.1700
Data Index: 7428961 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5817. Min Range: -6.5817
Max Act: 6.2067. Min Act: -0.1700
Data Index: 7594856 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19