Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3168 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.9560. Min Act: -0.1700
Data Index: 8305495 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.7060. Min Act: -0.1700
Data Index: 214066 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.5810. Min Act: -0.1700
Data Index: 5522927 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.5185. Min Act: -0.1700
Data Index: 2317145 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.4560. Min Act: -0.1700
Data Index: 5988940 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.4872. Min Act: -0.1700
Data Index: 535388 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.4560. Min Act: -0.1700
Data Index: 4377440 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.3622. Min Act: -0.1700
Data Index: 6904540 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.3935. Min Act: -0.1700
Data Index: 2297981 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.3935. Min Act: -0.1700
Data Index: 1047575 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.3310. Min Act: -0.1700
Data Index: 8171195 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.3622. Min Act: -0.1700
Data Index: 3869985 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.3622. Min Act: -0.1700
Data Index: 6841041 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.3310. Min Act: -0.1700
Data Index: 2303864 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.3310. Min Act: -0.1700
Data Index: 5011207 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.3310. Min Act: -0.1700
Data Index: 4623844 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.2997. Min Act: -0.1700
Data Index: 6500276 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.2997. Min Act: -0.1700
Data Index: 2712283 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.2997. Min Act: -0.1700
Data Index: 5976966 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9560. Min Range: -4.9560
Max Act: 4.2685. Min Act: -0.1700
Data Index: 5829008 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19