Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3161 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6265. Min Range: -8.6265
Max Act: 8.6265. Min Act: -0.1700
Data Index: 5370550 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6265. Min Range: -8.6265
Max Act: 8.3765. Min Act: -0.1700
Data Index: 738584 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.9390. Min Act: -0.1700
Data Index: 7125055 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.9390. Min Act: -0.1700
Data Index: 5930535 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.8140. Min Act: -0.1700
Data Index: 7272194 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.7515. Min Act: -0.1700
Data Index: 1845670 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.6890. Min Act: -0.1700
Data Index: 4344432 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.6890. Min Act: -0.1700
Data Index: 4664940 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.6265. Min Act: -0.1700
Data Index: 8239023 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.5640. Min Act: -0.1700
Data Index: 4924523 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.5640. Min Act: -0.1700
Data Index: 4642933 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.5640. Min Act: -0.1700
Data Index: 3240960 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.5328. Min Act: -0.1700
Data Index: 3559187 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.5015. Min Act: -0.1700
Data Index: 5043129 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.5015. Min Act: -0.1700
Data Index: 4713543 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.5328. Min Act: -0.1700
Data Index: 1466521 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.5015. Min Act: -0.1700
Data Index: 5335389 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.5015. Min Act: -0.1700
Data Index: 71371 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.4703. Min Act: -0.1700
Data Index: 6649249 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6265. Min Range: -8.6265
Max Act: 7.4703. Min Act: -0.1700
Data Index: 2800938 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19