Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2965 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3957. Min Range: -5.3957
Max Act: 5.3957. Min Act: -0.1700
Data Index: 7933138 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3957. Min Range: -5.3957
Max Act: 5.2707. Min Act: -0.1700
Data Index: 8763967 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3957. Min Range: -5.3957
Max Act: 5.0832. Min Act: -0.1700
Data Index: 881451 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3957. Min Range: -5.3957
Max Act: 5.0520. Min Act: -0.1700
Data Index: 4834697 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3957. Min Range: -5.3957
Max Act: 5.0520. Min Act: -0.1700
Data Index: 3687618 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.9582. Min Act: -0.1700
Data Index: 1966987 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.9270. Min Act: -0.1700
Data Index: 4496159 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.9270. Min Act: -0.1700
Data Index: 3642571 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.9270. Min Act: -0.1700
Data Index: 5823981 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.8957. Min Act: -0.1700
Data Index: 7376462 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.8957. Min Act: -0.1700
Data Index: 6990478 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.8957. Min Act: -0.1700
Data Index: 8606304 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.8957. Min Act: -0.1700
Data Index: 1663388 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.8957. Min Act: -0.1700
Data Index: 6710452 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.8645. Min Act: -0.1700
Data Index: 2957157 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.8332. Min Act: -0.1700
Data Index: 8397293 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.8332. Min Act: -0.1700
Data Index: 5763455 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.8020. Min Act: -0.1700
Data Index: 7352574 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.8332. Min Act: -0.1700
Data Index: 5287470 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3957. Min Range: -5.3957
Max Act: 4.7707. Min Act: -0.1700
Data Index: 8264122 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19