Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3388 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.5529. Min Act: -0.1700
Data Index: 3829048 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.3967. Min Act: -0.1700
Data Index: 7413214 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.3654. Min Act: -0.1700
Data Index: 8495287 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5529. Min Range: -7.5529
Max Act: 7.0529. Min Act: -0.1700
Data Index: 7700824 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.9279. Min Act: -0.1700
Data Index: 8398863 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.9279. Min Act: -0.1700
Data Index: 3889108 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.8654. Min Act: -0.1700
Data Index: 6239269 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.8342. Min Act: -0.1700
Data Index: 6631192 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.7717. Min Act: -0.1700
Data Index: 4141946 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.7404. Min Act: -0.1700
Data Index: 834275 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.7092. Min Act: -0.1700
Data Index: 4377 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.7092. Min Act: -0.1700
Data Index: 6828053 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.6779. Min Act: -0.1700
Data Index: 6267289 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.6779. Min Act: -0.1700
Data Index: 2313821 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.6467. Min Act: -0.1700
Data Index: 8510493 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.6467. Min Act: -0.1700
Data Index: 560085 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.6154. Min Act: -0.1700
Data Index: 5105236 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.6154. Min Act: -0.1700
Data Index: 1490015 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.5842. Min Act: -0.1700
Data Index: 7806276 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5529. Min Range: -7.5529
Max Act: 6.5529. Min Act: -0.1700
Data Index: 4425442 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19