Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2538 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.7228. Min Act: -0.1700
Data Index: 6428047 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.6290. Min Act: -0.1700
Data Index: 8418098 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.5353. Min Act: -0.1700
Data Index: 4081254 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.5353. Min Act: -0.1700
Data Index: 569677 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.5353. Min Act: -0.1700
Data Index: 1166677 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.5040. Min Act: -0.1700
Data Index: 301574 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.5040. Min Act: -0.1700
Data Index: 4421343 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.5353. Min Act: -0.1700
Data Index: 1790122 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.5040. Min Act: -0.1700
Data Index: 6600068 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.4728. Min Act: -0.1700
Data Index: 5586042 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.4728. Min Act: -0.1700
Data Index: 3377636 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.4415. Min Act: -0.1700
Data Index: 216941 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.4728. Min Act: -0.1700
Data Index: 5932071 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.4103. Min Act: -0.1700
Data Index: 3544740 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.4103. Min Act: -0.1700
Data Index: 2322197 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.3790. Min Act: -0.1700
Data Index: 2173334 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.3790. Min Act: -0.1700
Data Index: 977925 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.3478. Min Act: -0.1700
Data Index: 3651179 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.3790. Min Act: -0.1700
Data Index: 1764970 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7228. Min Range: -5.7228
Max Act: 5.3478. Min Act: -0.1700
Data Index: 4042867 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19