Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4709 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4078. Min Range: -6.4078
Max Act: 6.4078. Min Act: -0.1700
Data Index: 2195285 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4078. Min Range: -6.4078
Max Act: 6.1578. Min Act: -0.1700
Data Index: 5821059 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4078. Min Range: -6.4078
Max Act: 6.1578. Min Act: -0.1700
Data Index: 7131182 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4078. Min Range: -6.4078
Max Act: 6.1265. Min Act: -0.1700
Data Index: 84599 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4078. Min Range: -6.4078
Max Act: 6.0953. Min Act: -0.1700
Data Index: 5826584 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4078. Min Range: -6.4078
Max Act: 6.0953. Min Act: -0.1700
Data Index: 3413564 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4078. Min Range: -6.4078
Max Act: 6.0640. Min Act: -0.1700
Data Index: 7878637 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4078. Min Range: -6.4078
Max Act: 6.0015. Min Act: -0.1700
Data Index: 4643420 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4078. Min Range: -6.4078
Max Act: 6.0015. Min Act: -0.1700
Data Index: 6928428 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4078. Min Range: -6.4078
Max Act: 5.9703. Min Act: -0.1700
Data Index: 4037327 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4078. Min Range: -6.4078
Max Act: 5.9703. Min Act: -0.1700
Data Index: 4640132 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4078. Min Range: -6.4078
Max Act: 5.9703. Min Act: -0.1700
Data Index: 5228103 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4078. Min Range: -6.4078
Max Act: 5.9078. Min Act: -0.1700
Data Index: 7905612 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4078. Min Range: -6.4078
Max Act: 5.9078. Min Act: -0.1700
Data Index: 7300514 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4078. Min Range: -6.4078
Max Act: 5.8765. Min Act: -0.1700
Data Index: 3141291 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4078. Min Range: -6.4078
Max Act: 5.8765. Min Act: -0.1700
Data Index: 6058988 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4078. Min Range: -6.4078
Max Act: 5.8765. Min Act: -0.1700
Data Index: 5240935 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4078. Min Range: -6.4078
Max Act: 5.8453. Min Act: -0.1700
Data Index: 2405248 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4078. Min Range: -6.4078
Max Act: 5.8453. Min Act: -0.1700
Data Index: 6960784 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4078. Min Range: -6.4078
Max Act: 5.8453. Min Act: -0.1700
Data Index: 2438027 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19