Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1736 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.3043. Min Act: -0.1700
Data Index: 2252146 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.2105. Min Act: -0.1700
Data Index: 1541068 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1792. Min Act: -0.1700
Data Index: 8784564 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1792. Min Act: -0.1700
Data Index: 899489 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1792. Min Act: -0.1700
Data Index: 3416214 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1480. Min Act: -0.1700
Data Index: 15707 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.0855. Min Act: -0.1700
Data Index: 6537229 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1167. Min Act: -0.1700
Data Index: 5731274 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1480. Min Act: -0.1700
Data Index: 1375901 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1167. Min Act: -0.1700
Data Index: 4617196 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1167. Min Act: -0.1700
Data Index: 6818794 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.0855. Min Act: -0.1700
Data Index: 118908 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1167. Min Act: -0.1700
Data Index: 4788490 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1167. Min Act: -0.1700
Data Index: 62023 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1167. Min Act: -0.1700
Data Index: 5277741 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.0855. Min Act: -0.1700
Data Index: 1621999 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.0855. Min Act: -0.1700
Data Index: 7038712 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.1167. Min Act: -0.1700
Data Index: 8077735 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.0542. Min Act: -0.1700
Data Index: 6382306 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3043. Min Range: -4.3043
Max Act: 4.0855. Min Act: -0.1700
Data Index: 579011 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19