Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 708 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.4380. Min Act: -0.1700
Data Index: 3752994 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3755. Min Act: -0.1700
Data Index: 5989789 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.4067. Min Act: -0.1700
Data Index: 5803997 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.4067. Min Act: -0.1700
Data Index: 876480 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.4067. Min Act: -0.1700
Data Index: 1712567 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.4067. Min Act: -0.1700
Data Index: 2700215 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3442. Min Act: -0.1700
Data Index: 5982104 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3130. Min Act: -0.1700
Data Index: 6051834 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3442. Min Act: -0.1700
Data Index: 910230 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3442. Min Act: -0.1700
Data Index: 1655434 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3442. Min Act: -0.1700
Data Index: 1337667 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3442. Min Act: -0.1700
Data Index: 8249896 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3442. Min Act: -0.1700
Data Index: 3119177 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3442. Min Act: -0.1700
Data Index: 1529249 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.2817. Min Act: -0.1700
Data Index: 5894738 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3130. Min Act: -0.1700
Data Index: 5397010 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.2817. Min Act: -0.1700
Data Index: 2416194 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.2817. Min Act: -0.1700
Data Index: 1469287 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.2817. Min Act: -0.1700
Data Index: 5915668 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.2817. Min Act: -0.1700
Data Index: 4277208 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19