Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.7668. Min Act: -0.1700
Data Index: 4797086 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.7043. Min Act: -0.1700
Data Index: 662508 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.6105. Min Act: -0.1700
Data Index: 2536194 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5793. Min Act: -0.1700
Data Index: 461182 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5793. Min Act: -0.1700
Data Index: 1723058 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.5168. Min Act: -0.1700
Data Index: 5199754 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.4855. Min Act: -0.1700
Data Index: 6344118 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.4855. Min Act: -0.1700
Data Index: 4809769 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.4543. Min Act: -0.1700
Data Index: 3231501 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.3918. Min Act: -0.1700
Data Index: 655322 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.3605. Min Act: -0.1700
Data Index: 698630 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.3293. Min Act: -0.1700
Data Index: 5634769 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.3293. Min Act: -0.1700
Data Index: 1475094 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.2980. Min Act: -0.1700
Data Index: 7243385 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.3293. Min Act: -0.1700
Data Index: 3489953 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.2980. Min Act: -0.1700
Data Index: 1114088 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.2668. Min Act: -0.1700
Data Index: 8331953 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.2980. Min Act: -0.1700
Data Index: 4097279 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.2980. Min Act: -0.1700
Data Index: 2193886 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7668. Min Range: -4.7668
Max Act: 4.2668. Min Act: -0.1700
Data Index: 5353223 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19