Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.5595. Min Act: -0.1700
Data Index: 6291278 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.4185. Min Act: -0.1700
Data Index: 4486194 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.2773. Min Act: -0.1700
Data Index: 3501972 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.2616. Min Act: -0.1700
Data Index: 6805796 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.2616. Min Act: -0.1700
Data Index: 6850322 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.2616. Min Act: -0.1700
Data Index: 4592510 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.2302. Min Act: -0.1700
Data Index: 633039 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.2145. Min Act: -0.1700
Data Index: 4690980 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1988. Min Act: -0.1700
Data Index: 6633350 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1830. Min Act: -0.1700
Data Index: 6666696 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1516. Min Act: -0.1700
Data Index: 3472894 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1516. Min Act: -0.1700
Data Index: 3701155 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1201. Min Act: -0.1700
Data Index: 8683802 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1201. Min Act: -0.1700
Data Index: 8345344 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1043. Min Act: -0.1700
Data Index: 4165152 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1201. Min Act: -0.1700
Data Index: 3201063 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1201. Min Act: -0.1700
Data Index: 6541447 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1201. Min Act: -0.1700
Data Index: 8388240 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1043. Min Act: -0.1700
Data Index: 3067463 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5595. Min Range: -3.5595
Max Act: 3.1201. Min Act: -0.1700
Data Index: 7226303 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19