Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0568. Min Range: -7.0568
Max Act: 7.0568. Min Act: -0.1700
Data Index: 132284 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0568. Min Range: -7.0568
Max Act: 7.0568. Min Act: -0.1700
Data Index: 3338075 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.8380. Min Act: -0.1700
Data Index: 1401727 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.8068. Min Act: -0.1700
Data Index: 996174 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.7755. Min Act: -0.1700
Data Index: 7176907 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.7443. Min Act: -0.1700
Data Index: 7176908 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.7443. Min Act: -0.1700
Data Index: 3659990 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.7443. Min Act: -0.1700
Data Index: 5080271 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.7130. Min Act: -0.1700
Data Index: 8436942 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.6818. Min Act: -0.1700
Data Index: 4732430 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.6818. Min Act: -0.1700
Data Index: 8082112 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.6818. Min Act: -0.1700
Data Index: 2381298 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.6193. Min Act: -0.1700
Data Index: 635561 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.6193. Min Act: -0.1700
Data Index: 5153682 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.5568. Min Act: -0.1700
Data Index: 4447257 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.5880. Min Act: -0.1700
Data Index: 2896955 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.5568. Min Act: -0.1700
Data Index: 6857943 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.5568. Min Act: -0.1700
Data Index: 4584627 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.5255. Min Act: -0.1700
Data Index: 3706155 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0568. Min Range: -7.0568
Max Act: 6.5255. Min Act: -0.1700
Data Index: 7781220 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19