Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4676 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6199. Min Range: -7.6199
Max Act: 7.6199. Min Act: -0.1700
Data Index: 1927185 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6199. Min Range: -7.6199
Max Act: 7.4949. Min Act: -0.1700
Data Index: 451714 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6199. Min Range: -7.6199
Max Act: 7.3074. Min Act: -0.1700
Data Index: 6077957 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6199. Min Range: -7.6199
Max Act: 7.1512. Min Act: -0.1700
Data Index: 7421514 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6199. Min Range: -7.6199
Max Act: 7.1512. Min Act: -0.1700
Data Index: 558438 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6199. Min Range: -7.6199
Max Act: 7.0887. Min Act: -0.1700
Data Index: 2854087 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6199. Min Range: -7.6199
Max Act: 7.0574. Min Act: -0.1700
Data Index: 6349031 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6199. Min Range: -7.6199
Max Act: 7.0262. Min Act: -0.1700
Data Index: 3528499 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6199. Min Range: -7.6199
Max Act: 7.0262. Min Act: -0.1700
Data Index: 4503531 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6199. Min Range: -7.6199
Max Act: 6.9949. Min Act: -0.1700
Data Index: 760852 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6199. Min Range: -7.6199
Max Act: 6.9637. Min Act: -0.1700
Data Index: 6793060 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6199. Min Range: -7.6199
Max Act: 6.9637. Min Act: -0.1700
Data Index: 2380126 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6199. Min Range: -7.6199
Max Act: 6.9324. Min Act: -0.1700
Data Index: 2610813 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6199. Min Range: -7.6199
Max Act: 6.9324. Min Act: -0.1700
Data Index: 3542717 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6199. Min Range: -7.6199
Max Act: 6.9324. Min Act: -0.1700
Data Index: 8323665 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6199. Min Range: -7.6199
Max Act: 6.9324. Min Act: -0.1700
Data Index: 4297749 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6199. Min Range: -7.6199
Max Act: 6.9324. Min Act: -0.1700
Data Index: 3325092 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6199. Min Range: -7.6199
Max Act: 6.9012. Min Act: -0.1700
Data Index: 2104958 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6199. Min Range: -7.6199
Max Act: 6.9012. Min Act: -0.1700
Data Index: 1321291 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6199. Min Range: -7.6199
Max Act: 6.8699. Min Act: -0.1700
Data Index: 5369874 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19