Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.3518. Min Act: -0.1700
Data Index: 1094022 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.2576. Min Act: -0.1700
Data Index: 1631069 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.2733. Min Act: -0.1700
Data Index: 5438130 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.2261. Min Act: -0.1700
Data Index: 3855036 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.2261. Min Act: -0.1700
Data Index: 1589557 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.1947. Min Act: -0.1700
Data Index: 6027995 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.1632. Min Act: -0.1700
Data Index: 4959946 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.1790. Min Act: -0.1700
Data Index: 6879678 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.1475. Min Act: -0.1700
Data Index: 3977054 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.1475. Min Act: -0.1700
Data Index: 1545618 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.1160. Min Act: -0.1700
Data Index: 7611035 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.1160. Min Act: -0.1700
Data Index: 6874301 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.0845. Min Act: -0.1700
Data Index: 8134446 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.1160. Min Act: -0.1700
Data Index: 2906776 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.1317. Min Act: -0.1700
Data Index: 7363497 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.0845. Min Act: -0.1700
Data Index: 3900109 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.0529. Min Act: -0.1700
Data Index: 6988899 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.0529. Min Act: -0.1700
Data Index: 5389094 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.0687. Min Act: -0.1700
Data Index: 3160166 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3518. Min Range: -3.3518
Max Act: 3.0687. Min Act: -0.1700
Data Index: 6293516 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19