Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.1869. Min Act: -0.1700
Data Index: 7832424 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.1557. Min Act: -0.1700
Data Index: 2910089 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.1244. Min Act: -0.1700
Data Index: 708549 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.1244. Min Act: -0.1700
Data Index: 897517 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.1244. Min Act: -0.1700
Data Index: 4907952 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0932. Min Act: -0.1700
Data Index: 1819376 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0619. Min Act: -0.1700
Data Index: 5253951 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0932. Min Act: -0.1700
Data Index: 7262358 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0619. Min Act: -0.1700
Data Index: 6796274 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0619. Min Act: -0.1700
Data Index: 7521594 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 5884892 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 2855576 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 2079382 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 2862307 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 5253950 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 1696117 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9994. Min Act: -0.1700
Data Index: 577877 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9994. Min Act: -0.1700
Data Index: 4741472 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9994. Min Act: -0.1700
Data Index: 2440094 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9994. Min Act: -0.1700
Data Index: 1744212 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19