Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4984 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.4957. Min Act: -0.1700
Data Index: 2234360 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.4645. Min Act: -0.1700
Data Index: 4879190 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.4020. Min Act: -0.1700
Data Index: 4328160 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.3395. Min Act: -0.1700
Data Index: 7492904 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.3395. Min Act: -0.1700
Data Index: 7060106 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.3707. Min Act: -0.1700
Data Index: 8203940 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.3082. Min Act: -0.1700
Data Index: 6008124 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.3395. Min Act: -0.1700
Data Index: 4550213 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.3082. Min Act: -0.1700
Data Index: 6203446 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.2145. Min Act: -0.1700
Data Index: 4566088 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.2457. Min Act: -0.1700
Data Index: 2091415 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.2145. Min Act: -0.1700
Data Index: 3109657 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.2145. Min Act: -0.1700
Data Index: 5747527 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.2145. Min Act: -0.1700
Data Index: 982942 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.2145. Min Act: -0.1700
Data Index: 2109310 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.1832. Min Act: -0.1698
Data Index: 153774 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.1832. Min Act: -0.1700
Data Index: 6977664 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.0895. Min Act: -0.1700
Data Index: 6139843 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.1207. Min Act: -0.1700
Data Index: 428633 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4957. Min Range: -4.4957
Max Act: 4.0895. Min Act: -0.1700
Data Index: 4536255 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19