Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3851 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.8172. Min Act: -0.1700
Data Index: 7226946 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.8172. Min Act: -0.1700
Data Index: 2550160 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.5047. Min Act: -0.1700
Data Index: 3588958 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.4422. Min Act: -0.1700
Data Index: 7307677 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.4422. Min Act: -0.1700
Data Index: 6896006 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.3797. Min Act: -0.1700
Data Index: 730160 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.3797. Min Act: -0.1700
Data Index: 1449307 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.2547. Min Act: -0.1700
Data Index: 6240741 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.3172. Min Act: -0.1700
Data Index: 3136562 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.3172. Min Act: -0.1700
Data Index: 7942890 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.3172. Min Act: -0.1700
Data Index: 5660646 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.2547. Min Act: -0.1700
Data Index: 1359445 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.2547. Min Act: -0.1700
Data Index: 5875094 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.2547. Min Act: -0.1700
Data Index: 2787252 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.2547. Min Act: -0.1700
Data Index: 3060596 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.2547. Min Act: -0.1700
Data Index: 6286117 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.3172. Min Act: -0.1700
Data Index: 1496962 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.1922. Min Act: -0.1700
Data Index: 6940059 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.1922. Min Act: -0.1700
Data Index: 6990286 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8172. Min Range: -8.8172
Max Act: 8.2547. Min Act: -0.1700
Data Index: 148398 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19