Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 180 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0136. Min Range: -8.0136
Max Act: 8.0136. Min Act: -0.1700
Data Index: 6834748 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.7011. Min Act: -0.1700
Data Index: 6194066 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.7011. Min Act: -0.1700
Data Index: 7618821 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.7636. Min Act: -0.1700
Data Index: 7714197 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.5761. Min Act: -0.1700
Data Index: 2457135 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.5136. Min Act: -0.1700
Data Index: 1207842 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.5136. Min Act: -0.1700
Data Index: 4188919 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.4511. Min Act: -0.1700
Data Index: 4621551 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.5136. Min Act: -0.1700
Data Index: 4296058 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.5136. Min Act: -0.1700
Data Index: 2148080 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.4199. Min Act: -0.1700
Data Index: 1896107 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.3886. Min Act: -0.1700
Data Index: 2150667 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.4199. Min Act: -0.1700
Data Index: 3477224 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.3886. Min Act: -0.1700
Data Index: 6339831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.3886. Min Act: -0.1700
Data Index: 4035346 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.3886. Min Act: -0.1700
Data Index: 7323575 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.3574. Min Act: -0.1700
Data Index: 7233021 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.3574. Min Act: -0.1700
Data Index: 4940846 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.3574. Min Act: -0.1700
Data Index: 5123369 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0136. Min Range: -8.0136
Max Act: 7.3574. Min Act: -0.1700
Data Index: 542011 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19