Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.5367. Min Act: -0.1700
Data Index: 6878050 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.5054. Min Act: -0.1700
Data Index: 6878057 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.5054. Min Act: -0.1700
Data Index: 4380019 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.1616. Min Act: -0.1700
Data Index: 7856015 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.0991. Min Act: -0.1700
Data Index: 669492 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.0679. Min Act: -0.1700
Data Index: 2589262 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.0366. Min Act: -0.1700
Data Index: 2437198 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.0366. Min Act: -0.1700
Data Index: 5572531 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.0366. Min Act: -0.1700
Data Index: 7687255 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.0053. Min Act: -0.1700
Data Index: 5456183 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.0053. Min Act: -0.1700
Data Index: 738616 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.0053. Min Act: -0.1700
Data Index: 5225381 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.0053. Min Act: -0.1700
Data Index: 2727256 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5367. Min Range: -4.5367
Max Act: 3.9741. Min Act: -0.1700
Data Index: 5880618 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5367. Min Range: -4.5367
Max Act: 4.0053. Min Act: -0.1700
Data Index: 1020561 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5367. Min Range: -4.5367
Max Act: 3.9741. Min Act: -0.1700
Data Index: 5886056 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5367. Min Range: -4.5367
Max Act: 3.9428. Min Act: -0.1700
Data Index: 1484311 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5367. Min Range: -4.5367
Max Act: 3.9428. Min Act: -0.1700
Data Index: 5630207 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5367. Min Range: -4.5367
Max Act: 3.9428. Min Act: -0.1700
Data Index: 2572797 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5367. Min Range: -4.5367
Max Act: 3.9116. Min Act: -0.1700
Data Index: 3536383 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19