Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1263. Min Range: -6.1263
Max Act: 6.1263. Min Act: -0.1700
Data Index: 3898086 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.8138. Min Act: -0.1700
Data Index: 192944 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.4700. Min Act: -0.1700
Data Index: 7809434 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.3450. Min Act: -0.1700
Data Index: 818680 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.3450. Min Act: -0.1700
Data Index: 141802 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.3450. Min Act: -0.1700
Data Index: 1159209 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.3450. Min Act: -0.1700
Data Index: 1723502 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.1575. Min Act: -0.1700
Data Index: 2101075 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.1575. Min Act: -0.1700
Data Index: 3166182 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.0638. Min Act: -0.1700
Data Index: 1074520 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.0638. Min Act: -0.1700
Data Index: 5001104 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.0638. Min Act: -0.1700
Data Index: 1857209 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.0638. Min Act: -0.1700
Data Index: 2372009 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.0325. Min Act: -0.1694
Data Index: 8074583 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.0325. Min Act: -0.1700
Data Index: 6532727 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.0013. Min Act: -0.1700
Data Index: 8195838 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.0013. Min Act: -0.1696
Data Index: 2508829 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.0013. Min Act: -0.1700
Data Index: 609995 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1263. Min Range: -6.1263
Max Act: 5.0013. Min Act: -0.1700
Data Index: 7262064 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1263. Min Range: -6.1263
Max Act: 4.9388. Min Act: -0.1700
Data Index: 5246405 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19