Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1871 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.9586. Min Act: -0.1700
Data Index: 6045400 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.9586. Min Act: -0.1700
Data Index: 3749369 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.9273. Min Act: -0.1700
Data Index: 5218399 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.8961. Min Act: -0.1700
Data Index: 4089938 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.8648. Min Act: -0.1700
Data Index: 3752952 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.8336. Min Act: -0.1700
Data Index: 732980 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.8648. Min Act: -0.1700
Data Index: 6010187 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.8336. Min Act: -0.1700
Data Index: 5394838 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.8336. Min Act: -0.1700
Data Index: 7210623 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.8336. Min Act: -0.1700
Data Index: 3551062 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.8023. Min Act: -0.1700
Data Index: 8374357 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.8336. Min Act: -0.1700
Data Index: 7227136 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.8023. Min Act: -0.1700
Data Index: 7535738 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.7711. Min Act: -0.1700
Data Index: 3741692 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.7398. Min Act: -0.1700
Data Index: 3074901 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.7711. Min Act: -0.1700
Data Index: 5565447 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.7398. Min Act: -0.1700
Data Index: 6005581 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.7711. Min Act: -0.1700
Data Index: 725158 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.7711. Min Act: -0.1700
Data Index: 1994397 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9586. Min Range: -6.9586
Max Act: 6.7398. Min Act: -0.1700
Data Index: 5618435 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19