Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3080 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2661. Min Range: -7.2661
Max Act: 7.2661. Min Act: -0.1700
Data Index: 5366595 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2661. Min Range: -7.2661
Max Act: 7.2661. Min Act: -0.1700
Data Index: 6583583 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2661. Min Range: -7.2661
Max Act: 7.0786. Min Act: -0.1700
Data Index: 4449917 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2661. Min Range: -7.2661
Max Act: 7.0473. Min Act: -0.1700
Data Index: 7146320 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2661. Min Range: -7.2661
Max Act: 7.0786. Min Act: -0.1700
Data Index: 3174618 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2661. Min Range: -7.2661
Max Act: 7.0161. Min Act: -0.1700
Data Index: 98122 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.9223. Min Act: -0.1700
Data Index: 6993807 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.9536. Min Act: -0.1700
Data Index: 3772638 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.8911. Min Act: -0.1700
Data Index: 2438480 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.8911. Min Act: -0.1700
Data Index: 6317383 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.8911. Min Act: -0.1700
Data Index: 2600535 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.8911. Min Act: -0.1700
Data Index: 4449921 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.8911. Min Act: -0.1700
Data Index: 4804141 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.8598. Min Act: -0.1700
Data Index: 3517922 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.8286. Min Act: -0.1700
Data Index: 2765095 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.7973. Min Act: -0.1700
Data Index: 6438083 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.7973. Min Act: -0.1700
Data Index: 8701902 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.7348. Min Act: -0.1700
Data Index: 8643868 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.7661. Min Act: -0.1700
Data Index: 660940 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2661. Min Range: -7.2661
Max Act: 6.7661. Min Act: -0.1700
Data Index: 8453028 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19