Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 144 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.9489. Min Act: -0.1700
Data Index: 8670132 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.9176. Min Act: -0.1700
Data Index: 4776042 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.8864. Min Act: -0.1700
Data Index: 5004793 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.8239. Min Act: -0.1700
Data Index: 3045890 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.7614. Min Act: -0.1700
Data Index: 5662028 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6676. Min Act: -0.1700
Data Index: 5759110 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6989. Min Act: -0.1700
Data Index: 8171180 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6989. Min Act: -0.1700
Data Index: 643832 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6676. Min Act: -0.1700
Data Index: 729544 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6364. Min Act: -0.1700
Data Index: 3509935 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6051. Min Act: -0.1700
Data Index: 920327 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6051. Min Act: -0.1700
Data Index: 8574877 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.5739. Min Act: -0.1700
Data Index: 5202290 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6051. Min Act: -0.1700
Data Index: 210751 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.5426. Min Act: -0.1700
Data Index: 3904255 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.5426. Min Act: -0.1700
Data Index: 5208502 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.5426. Min Act: -0.1700
Data Index: 5011947 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.5426. Min Act: -0.1700
Data Index: 1098519 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.5426. Min Act: -0.1700
Data Index: 2893251 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.5426. Min Act: -0.1700
Data Index: 8466184 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19