Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4038 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.4386. Min Act: -0.1700
Data Index: 2133849 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.4073. Min Act: -0.1700
Data Index: 6118795 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.4073. Min Act: -0.1700
Data Index: 1410569 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.4073. Min Act: -0.1700
Data Index: 1692968 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.4073. Min Act: -0.1700
Data Index: 4800129 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3761. Min Act: -0.1700
Data Index: 2586067 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3448. Min Act: -0.1700
Data Index: 4808162 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3448. Min Act: -0.1700
Data Index: 3142156 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3448. Min Act: -0.1700
Data Index: 3575417 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3448. Min Act: -0.1700
Data Index: 3237285 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.2823. Min Act: -0.1700
Data Index: 2743430 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3448. Min Act: -0.1700
Data Index: 5167187 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3136. Min Act: -0.1700
Data Index: 3147134 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3136. Min Act: -0.1700
Data Index: 8543043 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3136. Min Act: -0.1700
Data Index: 6629055 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3448. Min Act: -0.1700
Data Index: 3076215 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3136. Min Act: -0.1700
Data Index: 1303380 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.2823. Min Act: -0.1700
Data Index: 5305188 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3136. Min Act: -0.1700
Data Index: 5945269 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.2823. Min Act: -0.1700
Data Index: 1212300 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19