Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2420 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.6206. Min Act: -0.1700
Data Index: 7605686 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.5268. Min Act: -0.1700
Data Index: 891811 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.5268. Min Act: -0.1700
Data Index: 4968220 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.4643. Min Act: -0.1700
Data Index: 3753169 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.4643. Min Act: -0.1700
Data Index: 634512 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.4956. Min Act: -0.1700
Data Index: 1105975 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.4643. Min Act: -0.1700
Data Index: 1394988 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.4331. Min Act: -0.1700
Data Index: 7512262 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.4018. Min Act: -0.1700
Data Index: 3608499 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.3706. Min Act: -0.1700
Data Index: 4929 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.3706. Min Act: -0.1700
Data Index: 2317092 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.4018. Min Act: -0.1700
Data Index: 844755 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.4018. Min Act: -0.1700
Data Index: 2365876 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.3706. Min Act: -0.1700
Data Index: 2617510 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.4018. Min Act: -0.1700
Data Index: 900984 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.3393. Min Act: -0.1700
Data Index: 393888 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.3393. Min Act: -0.1700
Data Index: 1329745 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.3393. Min Act: -0.1700
Data Index: 1031408 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.3393. Min Act: -0.1700
Data Index: 4058320 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6206. Min Range: -4.6206
Max Act: 4.3081. Min Act: -0.1700
Data Index: 4712980 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19