Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2868 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0253. Min Range: -5.0253
Max Act: 5.0253. Min Act: -0.1700
Data Index: 1776943 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.9628. Min Act: -0.1700
Data Index: 1304016 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.9316. Min Act: -0.1700
Data Index: 7097246 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.9316. Min Act: -0.1700
Data Index: 4083669 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.9316. Min Act: -0.1700
Data Index: 6725799 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.9003. Min Act: -0.1700
Data Index: 5875676 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.9003. Min Act: -0.1700
Data Index: 6041671 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8691. Min Act: -0.1700
Data Index: 7827056 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8691. Min Act: -0.1700
Data Index: 7118033 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8066. Min Act: -0.1700
Data Index: 5314274 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8378. Min Act: -0.1700
Data Index: 1950396 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8378. Min Act: -0.1700
Data Index: 4484318 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8378. Min Act: -0.1700
Data Index: 3330341 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8066. Min Act: -0.1700
Data Index: 8283730 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8066. Min Act: -0.1700
Data Index: 3460019 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8066. Min Act: -0.1700
Data Index: 7354341 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8066. Min Act: -0.1700
Data Index: 7877072 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8066. Min Act: -0.1700
Data Index: 2597110 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.7753. Min Act: -0.1700
Data Index: 1452263 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.7753. Min Act: -0.1700
Data Index: 4573496 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19