Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.3957. Min Act: -0.1700
Data Index: 2493387 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.2082. Min Act: -0.1700
Data Index: 5287184 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.2082. Min Act: -0.1700
Data Index: 1953010 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.1457. Min Act: -0.1700
Data Index: 8026230 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.0832. Min Act: -0.1700
Data Index: 8546240 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.0832. Min Act: -0.1700
Data Index: 1389445 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.0832. Min Act: -0.1700
Data Index: 5258488 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.0207. Min Act: -0.1700
Data Index: 3295341 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.0207. Min Act: -0.1700
Data Index: 7071090 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.0207. Min Act: -0.1700
Data Index: 3309873 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.0207. Min Act: -0.1700
Data Index: 2329143 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.0207. Min Act: -0.1700
Data Index: 2136650 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3957. Min Range: -9.3957
Max Act: 9.0207. Min Act: -0.1700
Data Index: 5172472 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3957. Min Range: -9.3957
Max Act: 8.9582. Min Act: -0.1700
Data Index: 6187566 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3957. Min Range: -9.3957
Max Act: 8.9582. Min Act: -0.1700
Data Index: 7072196 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3957. Min Range: -9.3957
Max Act: 8.9582. Min Act: -0.1700
Data Index: 7165334 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3957. Min Range: -9.3957
Max Act: 8.9582. Min Act: -0.1700
Data Index: 1437291 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3957. Min Range: -9.3957
Max Act: 8.9582. Min Act: -0.1700
Data Index: 5238744 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3957. Min Range: -9.3957
Max Act: 8.9582. Min Act: -0.1700
Data Index: 5232390 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3957. Min Range: -9.3957
Max Act: 8.9582. Min Act: -0.1700
Data Index: 5171023 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19