Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4640 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.4900. Min Act: -0.1700
Data Index: 875911 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.4587. Min Act: -0.1700
Data Index: 2526413 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.3650. Min Act: -0.1700
Data Index: 2710624 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.3337. Min Act: -0.1700
Data Index: 99950 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.2712. Min Act: -0.1700
Data Index: 3800925 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.2712. Min Act: -0.1700
Data Index: 5732954 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.2400. Min Act: -0.1700
Data Index: 2579029 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.2087. Min Act: -0.1700
Data Index: 3470806 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.1462. Min Act: -0.1700
Data Index: 6203862 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.1462. Min Act: -0.1700
Data Index: 7099720 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.1462. Min Act: -0.1700
Data Index: 7437141 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.1462. Min Act: -0.1700
Data Index: 3248032 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.1150. Min Act: -0.1700
Data Index: 5894118 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.1150. Min Act: -0.1700
Data Index: 7795645 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.1150. Min Act: -0.1700
Data Index: 6809630 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.0837. Min Act: -0.1700
Data Index: 6939517 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.0837. Min Act: -0.1700
Data Index: 4775156 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.0837. Min Act: -0.1700
Data Index: 5732953 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.1150. Min Act: -0.1700
Data Index: 5090513 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4900. Min Range: -5.4900
Max Act: 5.0837. Min Act: -0.1700
Data Index: 4889497 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19