Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5702 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.7304. Min Act: -0.1700
Data Index: 2878322 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.6366. Min Act: -0.1700
Data Index: 6032765 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5116. Min Act: -0.1700
Data Index: 3767731 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.5116. Min Act: -0.1700
Data Index: 6944257 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.4179. Min Act: -0.1700
Data Index: 6498258 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.4179. Min Act: -0.1700
Data Index: 6619036 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.4179. Min Act: -0.1700
Data Index: 853645 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.3866. Min Act: -0.1700
Data Index: 3512064 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.3866. Min Act: -0.1700
Data Index: 7968060 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.3241. Min Act: -0.1700
Data Index: 6091680 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.3241. Min Act: -0.1700
Data Index: 7226083 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.3241. Min Act: -0.1700
Data Index: 2841578 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.2929. Min Act: -0.1700
Data Index: 7132399 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.2929. Min Act: -0.1700
Data Index: 245565 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.2616. Min Act: -0.1700
Data Index: 6420331 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.2616. Min Act: -0.1700
Data Index: 1967450 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.2616. Min Act: -0.1700
Data Index: 4907851 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.2304. Min Act: -0.1700
Data Index: 5812156 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.2304. Min Act: -0.1700
Data Index: 2243020 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7304. Min Range: -5.7304
Max Act: 5.1991. Min Act: -0.1700
Data Index: 7595209 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19