Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6080. Min Range: -8.6080
Max Act: 8.6080. Min Act: -0.1700
Data Index: 7743473 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.4830. Min Act: -0.1700
Data Index: 6124542 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.4830. Min Act: -0.1700
Data Index: 140942 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.4518. Min Act: -0.1700
Data Index: 7593422 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.3580. Min Act: -0.1700
Data Index: 1239280 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.2955. Min Act: -0.1700
Data Index: 5241706 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.2955. Min Act: -0.1700
Data Index: 2766318 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.2330. Min Act: -0.1700
Data Index: 6789975 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.2330. Min Act: -0.1700
Data Index: 5159708 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.2018. Min Act: -0.1700
Data Index: 5791328 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.1705. Min Act: -0.1700
Data Index: 7359409 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.1080. Min Act: -0.1700
Data Index: 7009691 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.1080. Min Act: -0.1700
Data Index: 2133417 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.0455. Min Act: -0.1700
Data Index: 6780673 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.0768. Min Act: -0.1700
Data Index: 8799857 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.0768. Min Act: -0.1700
Data Index: 3343368 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.0768. Min Act: -0.1700
Data Index: 2411276 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.0455. Min Act: -0.1700
Data Index: 5834088 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.0143. Min Act: -0.1700
Data Index: 7978198 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6080. Min Range: -8.6080
Max Act: 7.0143. Min Act: -0.1700
Data Index: 1107568 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19