Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1706 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.9199. Min Act: -0.1700
Data Index: 2088075 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.6699. Min Act: -0.1700
Data Index: 6687169 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.6074. Min Act: -0.1700
Data Index: 7672539 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.5762. Min Act: -0.1700
Data Index: 8725341 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.5762. Min Act: -0.1700
Data Index: 254689 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.5137. Min Act: -0.1700
Data Index: 44119 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.4824. Min Act: -0.1700
Data Index: 8501068 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.4512. Min Act: -0.1700
Data Index: 4222604 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.4512. Min Act: -0.1700
Data Index: 3471111 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.4824. Min Act: -0.1700
Data Index: 5395932 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.4199. Min Act: -0.1700
Data Index: 5121347 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.3887. Min Act: -0.1700
Data Index: 2088072 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.3887. Min Act: -0.1700
Data Index: 6572352 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.3574. Min Act: -0.1700
Data Index: 7337100 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.3887. Min Act: -0.1700
Data Index: 8614492 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.3574. Min Act: -0.1700
Data Index: 3625336 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.3574. Min Act: -0.1700
Data Index: 6576253 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.3574. Min Act: -0.1700
Data Index: 3198017 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.3574. Min Act: -0.1700
Data Index: 2610827 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9199. Min Range: -4.9199
Max Act: 4.3262. Min Act: -0.1700
Data Index: 252775 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19