Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1024 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.4431. Min Act: -0.1700
Data Index: 4682251 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.4119. Min Act: -0.1700
Data Index: 6961256 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.4119. Min Act: -0.1700
Data Index: 8509133 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.3806. Min Act: -0.1700
Data Index: 5918075 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.2869. Min Act: -0.1700
Data Index: 5849537 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.2869. Min Act: -0.1700
Data Index: 8169508 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.2244. Min Act: -0.1700
Data Index: 696695 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.2244. Min Act: -0.1700
Data Index: 7244437 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.1931. Min Act: -0.1700
Data Index: 6654633 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.1619. Min Act: -0.1700
Data Index: 3802651 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.1619. Min Act: -0.1700
Data Index: 1824988 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.1931. Min Act: -0.1700
Data Index: 6372096 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.0994. Min Act: -0.1700
Data Index: 2231489 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.0681. Min Act: -0.1700
Data Index: 5293051 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.0681. Min Act: -0.1700
Data Index: 3709224 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.0681. Min Act: -0.1700
Data Index: 7809262 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.0681. Min Act: -0.1700
Data Index: 4175318 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.0369. Min Act: -0.1700
Data Index: 8516387 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4431. Min Range: -6.4431
Max Act: 6.0056. Min Act: -0.1700
Data Index: 198748 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4431. Min Range: -6.4431
Max Act: 5.9744. Min Act: -0.1700
Data Index: 3328649 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19