Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3154 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.2770. Min Act: -0.1700
Data Index: 7890464 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.2457. Min Act: -0.1700
Data Index: 6404036 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.2145. Min Act: -0.1700
Data Index: 3896813 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.2145. Min Act: -0.1700
Data Index: 8124216 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.1520. Min Act: -0.1700
Data Index: 715099 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.1520. Min Act: -0.1700
Data Index: 8297266 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.1207. Min Act: -0.1700
Data Index: 1084349 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.0270. Min Act: -0.1700
Data Index: 45310 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.0582. Min Act: -0.1700
Data Index: 5144638 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.0582. Min Act: -0.1700
Data Index: 2824899 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.0582. Min Act: -0.1700
Data Index: 5881245 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2770. Min Range: -4.2770
Max Act: 4.0270. Min Act: -0.1700
Data Index: 6436673 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2770. Min Range: -4.2770
Max Act: 3.9957. Min Act: -0.1700
Data Index: 4525156 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2770. Min Range: -4.2770
Max Act: 3.9957. Min Act: -0.1700
Data Index: 907592 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2770. Min Range: -4.2770
Max Act: 3.9644. Min Act: -0.1700
Data Index: 2608074 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2770. Min Range: -4.2770
Max Act: 3.9644. Min Act: -0.1700
Data Index: 452043 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2770. Min Range: -4.2770
Max Act: 3.9957. Min Act: -0.1700
Data Index: 2550840 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2770. Min Range: -4.2770
Max Act: 3.9644. Min Act: -0.1700
Data Index: 4320467 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2770. Min Range: -4.2770
Max Act: 3.9644. Min Act: -0.1700
Data Index: 2324540 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2770. Min Range: -4.2770
Max Act: 3.9332. Min Act: -0.1700
Data Index: 7420162 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19