Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.9664. Min Act: -0.1700
Data Index: 2624157 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.7476. Min Act: -0.1700
Data Index: 4631090 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.5914. Min Act: -0.1700
Data Index: 5496029 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.5601. Min Act: -0.1700
Data Index: 7891557 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.4976. Min Act: -0.1700
Data Index: 2963035 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.4664. Min Act: -0.1700
Data Index: 7855447 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.4351. Min Act: -0.1700
Data Index: 665167 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.4039. Min Act: -0.1700
Data Index: 2156458 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.4039. Min Act: -0.1700
Data Index: 2569620 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.3726. Min Act: -0.1700
Data Index: 8080927 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.3414. Min Act: -0.1700
Data Index: 286303 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.3101. Min Act: -0.1700
Data Index: 6095683 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.3101. Min Act: -0.1700
Data Index: 8571368 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.3101. Min Act: -0.1700
Data Index: 8604222 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.2789. Min Act: -0.1700
Data Index: 4978418 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.2789. Min Act: -0.1700
Data Index: 4864101 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.2789. Min Act: -0.1700
Data Index: 7583787 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.2789. Min Act: -0.1700
Data Index: 3308415 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.2789. Min Act: -0.1700
Data Index: 6580072 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9664. Min Range: -5.9664
Max Act: 5.2476. Min Act: -0.1700
Data Index: 4267970 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19