Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5351 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.4233. Min Act: -0.1700
Data Index: 8099969 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.4233. Min Act: -0.1700
Data Index: 5477633 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3920. Min Act: -0.1700
Data Index: 3571526 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3608. Min Act: -0.1700
Data Index: 6110991 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3608. Min Act: -0.1700
Data Index: 5783416 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3608. Min Act: -0.1700
Data Index: 5648758 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3608. Min Act: -0.1700
Data Index: 989603 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3295. Min Act: -0.1700
Data Index: 981338 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3295. Min Act: -0.1700
Data Index: 145435 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3295. Min Act: -0.1700
Data Index: 4591880 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3608. Min Act: -0.1700
Data Index: 2730312 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3608. Min Act: -0.1700
Data Index: 5299871 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3295. Min Act: -0.1700
Data Index: 7917354 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.3295. Min Act: -0.1700
Data Index: 4331424 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2983. Min Act: -0.1700
Data Index: 2281141 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2983. Min Act: -0.1700
Data Index: 8589850 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2983. Min Act: -0.1700
Data Index: 4180601 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2670. Min Act: -0.1700
Data Index: 7260333 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2670. Min Act: -0.1700
Data Index: 3784221 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4233. Min Range: -4.4233
Max Act: 4.2670. Min Act: -0.1700
Data Index: 2677212 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19