Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3530 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1301. Min Range: -7.1301
Max Act: 7.1301. Min Act: -0.1700
Data Index: 5529840 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1301. Min Range: -7.1301
Max Act: 7.0989. Min Act: -0.1700
Data Index: 8206215 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1301. Min Range: -7.1301
Max Act: 7.0676. Min Act: -0.1700
Data Index: 8206218 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1301. Min Range: -7.1301
Max Act: 7.0676. Min Act: -0.1700
Data Index: 2073770 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1301. Min Range: -7.1301
Max Act: 7.0051. Min Act: -0.1700
Data Index: 8206212 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.9739. Min Act: -0.1700
Data Index: 8562095 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.9426. Min Act: -0.1700
Data Index: 2233402 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.9426. Min Act: -0.1700
Data Index: 1502130 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.9114. Min Act: -0.1700
Data Index: 1766816 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.9114. Min Act: -0.1700
Data Index: 1766822 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.9114. Min Act: -0.1700
Data Index: 7243333 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.8801. Min Act: -0.1700
Data Index: 1619604 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.8176. Min Act: -0.1700
Data Index: 8206208 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.8489. Min Act: -0.1700
Data Index: 753731 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.8489. Min Act: -0.1700
Data Index: 1766820 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.8489. Min Act: -0.1700
Data Index: 1896514 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.8489. Min Act: -0.1700
Data Index: 7442742 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.7864. Min Act: -0.1700
Data Index: 7354412 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.8176. Min Act: -0.1700
Data Index: 1766827 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1301. Min Range: -7.1301
Max Act: 6.7864. Min Act: -0.1700
Data Index: 8206209 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19