Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2006 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2647. Min Range: -5.2647
Max Act: 5.2647. Min Act: -0.1700
Data Index: 5564156 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2647. Min Range: -5.2647
Max Act: 5.1085. Min Act: -0.1700
Data Index: 2297146 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.9835. Min Act: -0.1700
Data Index: 7007393 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.9522. Min Act: -0.1700
Data Index: 4141390 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.9210. Min Act: -0.1700
Data Index: 6008369 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.9210. Min Act: -0.1700
Data Index: 149090 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.9210. Min Act: -0.1700
Data Index: 332128 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.8585. Min Act: -0.1700
Data Index: 7493568 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.8897. Min Act: -0.1700
Data Index: 3755993 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.8272. Min Act: -0.1700
Data Index: 506671 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.8272. Min Act: -0.1700
Data Index: 7564118 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.7960. Min Act: -0.1700
Data Index: 500449 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.7960. Min Act: -0.1700
Data Index: 3192768 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.7647. Min Act: -0.1700
Data Index: 7756635 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.7335. Min Act: -0.1700
Data Index: 2946647 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.7647. Min Act: -0.1700
Data Index: 676098 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.7647. Min Act: -0.1700
Data Index: 1170331 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.7335. Min Act: -0.1700
Data Index: 4813263 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.7022. Min Act: -0.1700
Data Index: 80301 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2647. Min Range: -5.2647
Max Act: 4.7335. Min Act: -0.1700
Data Index: 4648251 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19