Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3316 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.3272. Min Act: -0.1700
Data Index: 7520143 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.2960. Min Act: -0.1700
Data Index: 7520149 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.1710. Min Act: -0.1700
Data Index: 7520156 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.1085. Min Act: -0.1700
Data Index: 7520139 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.0460. Min Act: -0.1700
Data Index: 7520176 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.0772. Min Act: -0.1700
Data Index: 7520165 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.0772. Min Act: -0.1700
Data Index: 7520171 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.0460. Min Act: -0.1700
Data Index: 7520166 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.0147. Min Act: -0.1700
Data Index: 7520170 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.0147. Min Act: -0.1700
Data Index: 7520150 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.0147. Min Act: -0.1700
Data Index: 7520175 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.9835. Min Act: -0.1700
Data Index: 7520173 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.9835. Min Act: -0.1700
Data Index: 7520140 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.9522. Min Act: -0.1700
Data Index: 7520153 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.9210. Min Act: -0.1700
Data Index: 7520145 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.8897. Min Act: -0.1700
Data Index: 7520148 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.8585. Min Act: -0.1700
Data Index: 7520158 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.8585. Min Act: -0.1700
Data Index: 7520157 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.7960. Min Act: -0.1700
Data Index: 293642 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.7647. Min Act: -0.1700
Data Index: 7520154 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19