Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.6712. Min Act: -0.1700
Data Index: 925623 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.5150. Min Act: -0.1700
Data Index: 4298270 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.4837. Min Act: -0.1700
Data Index: 4746203 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.3900. Min Act: -0.1700
Data Index: 1077138 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.3900. Min Act: -0.1700
Data Index: 6458773 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.3587. Min Act: -0.1700
Data Index: 5550637 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.3587. Min Act: -0.1700
Data Index: 1489482 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.3275. Min Act: -0.1700
Data Index: 6216859 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.3275. Min Act: -0.1700
Data Index: 4998814 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.2962. Min Act: -0.1700
Data Index: 4887902 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.2962. Min Act: -0.1700
Data Index: 6156613 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.2962. Min Act: -0.1700
Data Index: 2017359 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.2650. Min Act: -0.1700
Data Index: 6084170 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.2337. Min Act: -0.1700
Data Index: 6114710 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.2650. Min Act: -0.1700
Data Index: 813884 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.2650. Min Act: -0.1700
Data Index: 2528924 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.2337. Min Act: -0.1700
Data Index: 6183676 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.2337. Min Act: -0.1700
Data Index: 6335813 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.2337. Min Act: -0.1700
Data Index: 5284363 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6712. Min Range: -4.6712
Max Act: 4.2337. Min Act: -0.1700
Data Index: 2269952 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19