Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1748 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.3925. Min Act: -0.1700
Data Index: 560305 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.2988. Min Act: -0.1700
Data Index: 5302234 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.1113. Min Act: -0.1700
Data Index: 1706966 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.1113. Min Act: -0.1700
Data Index: 8713244 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.1113. Min Act: -0.1700
Data Index: 8209496 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.0800. Min Act: -0.1700
Data Index: 5193225 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.0175. Min Act: -0.1700
Data Index: 4521808 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.0175. Min Act: -0.1700
Data Index: 4779731 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3925. Min Range: -5.3925
Max Act: 5.0175. Min Act: -0.1700
Data Index: 4190204 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9862. Min Act: -0.1700
Data Index: 4809729 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9862. Min Act: -0.1700
Data Index: 1309271 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9550. Min Act: -0.1700
Data Index: 3746894 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9550. Min Act: -0.1700
Data Index: 3513947 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9550. Min Act: -0.1700
Data Index: 8357961 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9862. Min Act: -0.1700
Data Index: 8257829 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9237. Min Act: -0.1700
Data Index: 4177709 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9237. Min Act: -0.1700
Data Index: 6808968 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.9237. Min Act: -0.1700
Data Index: 3148726 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.8925. Min Act: -0.1700
Data Index: 7426673 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3925. Min Range: -5.3925
Max Act: 4.8925. Min Act: -0.1700
Data Index: 5971168 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19