Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.7138. Min Act: -0.1700
Data Index: 8649956 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.6201. Min Act: -0.1700
Data Index: 7425634 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.5263. Min Act: -0.1700
Data Index: 6754610 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.4951. Min Act: -0.1700
Data Index: 5437323 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.4638. Min Act: -0.1700
Data Index: 2932249 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.4638. Min Act: -0.1700
Data Index: 7011668 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.3388. Min Act: -0.1700
Data Index: 5814632 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.3388. Min Act: -0.1700
Data Index: 6389616 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.3388. Min Act: -0.1700
Data Index: 1915525 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.3388. Min Act: -0.1700
Data Index: 8755314 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.3701. Min Act: -0.1700
Data Index: 2532781 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.3076. Min Act: -0.1700
Data Index: 4653588 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.3076. Min Act: -0.1700
Data Index: 4653589 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.3076. Min Act: -0.1700
Data Index: 579148 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.3076. Min Act: -0.1700
Data Index: 6058649 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.2763. Min Act: -0.1700
Data Index: 6751804 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.2763. Min Act: -0.1700
Data Index: 8624090 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.2763. Min Act: -0.1700
Data Index: 1667788 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.2763. Min Act: -0.1700
Data Index: 8165164 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7138. Min Range: -5.7138
Max Act: 5.2451. Min Act: -0.1700
Data Index: 2189789 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19