Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5668 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4897. Min Range: -7.4897
Max Act: 7.4897. Min Act: -0.1700
Data Index: 7326309 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4897. Min Range: -7.4897
Max Act: 7.3334. Min Act: -0.1700
Data Index: 5195302 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.9897. Min Act: -0.1700
Data Index: 4928672 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.9272. Min Act: -0.1700
Data Index: 556115 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.8647. Min Act: -0.1700
Data Index: 5645556 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.8647. Min Act: -0.1700
Data Index: 8333813 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.7397. Min Act: -0.1700
Data Index: 4604128 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.7084. Min Act: -0.1700
Data Index: 5993237 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.7397. Min Act: -0.1700
Data Index: 4777159 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.7397. Min Act: -0.1700
Data Index: 5809795 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.6459. Min Act: -0.1700
Data Index: 5510122 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.6147. Min Act: -0.1700
Data Index: 6563598 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.6147. Min Act: -0.1700
Data Index: 7364676 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.5209. Min Act: -0.1700
Data Index: 796157 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.5209. Min Act: -0.1700
Data Index: 2118077 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.5209. Min Act: -0.1700
Data Index: 6613290 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.5209. Min Act: -0.1700
Data Index: 2620695 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.5209. Min Act: -0.1700
Data Index: 7696360 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.4584. Min Act: -0.1700
Data Index: 2588153 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4897. Min Range: -7.4897
Max Act: 6.4584. Min Act: -0.1700
Data Index: 6142603 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19