Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.3165. Min Act: -0.1700
Data Index: 3385952 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2671. Min Act: -0.1700
Data Index: 644726 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2506. Min Act: -0.1700
Data Index: 2272575 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2341. Min Act: -0.1700
Data Index: 3459214 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2341. Min Act: -0.1700
Data Index: 5846766 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2341. Min Act: -0.1700
Data Index: 8698533 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2341. Min Act: -0.1700
Data Index: 75837 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2175. Min Act: -0.1700
Data Index: 6610092 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2175. Min Act: -0.1700
Data Index: 7284091 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.1844. Min Act: -0.1700
Data Index: 4136443 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2010. Min Act: -0.1700
Data Index: 2719443 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.1844. Min Act: -0.1700
Data Index: 8136806 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2010. Min Act: -0.1700
Data Index: 6602657 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2010. Min Act: -0.1700
Data Index: 6304693 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.2010. Min Act: -0.1700
Data Index: 2297041 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.1844. Min Act: -0.1700
Data Index: 4006080 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.1844. Min Act: -0.1700
Data Index: 337359 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.1844. Min Act: -0.1700
Data Index: 3719245 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.1844. Min Act: -0.1700
Data Index: 2927646 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3165. Min Range: -2.3165
Max Act: 2.1844. Min Act: -0.1700
Data Index: 2943690 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19