Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.8387. Min Act: -0.1700
Data Index: 172265 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.7449. Min Act: -0.1700
Data Index: 172266 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.7137. Min Act: -0.1700
Data Index: 172267 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.6824. Min Act: -0.1700
Data Index: 5309181 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.6512. Min Act: -0.1700
Data Index: 1970359 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.6512. Min Act: -0.1700
Data Index: 2383134 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.6512. Min Act: -0.1700
Data Index: 5524983 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.5887. Min Act: -0.1700
Data Index: 1970360 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.5262. Min Act: -0.1700
Data Index: 2383137 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.5262. Min Act: -0.1700
Data Index: 1970358 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.5262. Min Act: -0.1700
Data Index: 8783945 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.4949. Min Act: -0.1700
Data Index: 2383138 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.4949. Min Act: -0.1700
Data Index: 3514952 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.4637. Min Act: -0.1700
Data Index: 2383140 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.4324. Min Act: -0.1700
Data Index: 2383135 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.4324. Min Act: -0.1700
Data Index: 2383136 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.4324. Min Act: -0.1700
Data Index: 3581743 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.4324. Min Act: -0.1700
Data Index: 1994034 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.3699. Min Act: -0.1700
Data Index: 2383139 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8387. Min Range: -6.8387
Max Act: 6.4012. Min Act: -0.1700
Data Index: 6753191 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19