Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 987 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2191. Min Range: -5.2191
Max Act: 5.2191. Min Act: -0.1700
Data Index: 26345 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2191. Min Range: -5.2191
Max Act: 5.0004. Min Act: -0.1700
Data Index: 3560649 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2191. Min Range: -5.2191
Max Act: 5.0004. Min Act: -0.1700
Data Index: 4002030 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.9691. Min Act: -0.1700
Data Index: 2437827 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.9379. Min Act: -0.1700
Data Index: 8605197 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.9066. Min Act: -0.1700
Data Index: 243243 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.8754. Min Act: -0.1700
Data Index: 4159504 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.9066. Min Act: -0.1700
Data Index: 5595739 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.9379. Min Act: -0.1700
Data Index: 1138454 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.9066. Min Act: -0.1700
Data Index: 2056672 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.9066. Min Act: -0.1700
Data Index: 6770463 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.9066. Min Act: -0.1700
Data Index: 5724845 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.8754. Min Act: -0.1700
Data Index: 7385856 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.8754. Min Act: -0.1700
Data Index: 4805756 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.8754. Min Act: -0.1700
Data Index: 4737620 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.8441. Min Act: -0.1700
Data Index: 970259 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.8754. Min Act: -0.1700
Data Index: 2486532 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.8754. Min Act: -0.1700
Data Index: 820835 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.8754. Min Act: -0.1700
Data Index: 6256199 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2191. Min Range: -5.2191
Max Act: 4.8441. Min Act: -0.1700
Data Index: 882402 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19