Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1377 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.9081. Min Act: -0.1700
Data Index: 4545189 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.8456. Min Act: -0.1700
Data Index: 6960344 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.8144. Min Act: -0.1700
Data Index: 68122 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.7831. Min Act: -0.1700
Data Index: 1944179 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.7831. Min Act: -0.1700
Data Index: 240330 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.7831. Min Act: -0.1700
Data Index: 8192389 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.7831. Min Act: -0.1700
Data Index: 3089306 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.7519. Min Act: -0.1700
Data Index: 5221041 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.7206. Min Act: -0.1700
Data Index: 2625503 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.7206. Min Act: -0.1700
Data Index: 7766348 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.6894. Min Act: -0.1700
Data Index: 2594834 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.6894. Min Act: -0.1700
Data Index: 7147893 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.6894. Min Act: -0.1700
Data Index: 7006436 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.6894. Min Act: -0.1700
Data Index: 8373416 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.6894. Min Act: -0.1700
Data Index: 3383753 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.6894. Min Act: -0.1700
Data Index: 5014283 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.6581. Min Act: -0.1700
Data Index: 2920117 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.6581. Min Act: -0.1700
Data Index: 420 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.6581. Min Act: -0.1700
Data Index: 4944241 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9081. Min Range: -4.9081
Max Act: 4.6581. Min Act: -0.1700
Data Index: 2333459 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19