Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2808 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3818. Min Range: -7.3818
Max Act: 7.3818. Min Act: -0.1700
Data Index: 7449764 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3818. Min Range: -7.3818
Max Act: 7.3193. Min Act: -0.1700
Data Index: 841076 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3818. Min Range: -7.3818
Max Act: 7.0693. Min Act: -0.1700
Data Index: 523711 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.9756. Min Act: -0.1700
Data Index: 6707548 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.9756. Min Act: -0.1700
Data Index: 4750658 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.9756. Min Act: -0.1700
Data Index: 7036567 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.9131. Min Act: -0.1700
Data Index: 8807259 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.9443. Min Act: -0.1700
Data Index: 4304374 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.9443. Min Act: -0.1700
Data Index: 2536635 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.8818. Min Act: -0.1700
Data Index: 7365836 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.8506. Min Act: -0.1700
Data Index: 380787 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.8193. Min Act: -0.1700
Data Index: 2454362 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.8193. Min Act: -0.1700
Data Index: 7707184 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.8193. Min Act: -0.1700
Data Index: 5840372 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.8193. Min Act: -0.1700
Data Index: 2421767 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.8193. Min Act: -0.1700
Data Index: 4979474 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.7881. Min Act: -0.1700
Data Index: 5144842 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.7568. Min Act: -0.1700
Data Index: 2758779 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.7256. Min Act: -0.1700
Data Index: 3372792 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3818. Min Range: -7.3818
Max Act: 6.7256. Min Act: -0.1700
Data Index: 1149528 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19