Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5020 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1306. Min Range: -6.1306
Max Act: 6.1306. Min Act: -0.1700
Data Index: 1128445 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1306. Min Range: -6.1306
Max Act: 6.0369. Min Act: -0.1700
Data Index: 1171490 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1306. Min Range: -6.1306
Max Act: 6.0056. Min Act: -0.1700
Data Index: 5167897 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.9431. Min Act: -0.1700
Data Index: 5725870 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.9119. Min Act: -0.1700
Data Index: 8484914 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.9119. Min Act: -0.1700
Data Index: 7877601 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8806. Min Act: -0.1700
Data Index: 4349365 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8806. Min Act: -0.1700
Data Index: 2058035 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8806. Min Act: -0.1700
Data Index: 6357148 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8806. Min Act: -0.1700
Data Index: 8804908 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8806. Min Act: -0.1700
Data Index: 6512280 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8806. Min Act: -0.1700
Data Index: 327624 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8181. Min Act: -0.1700
Data Index: 3554130 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8494. Min Act: -0.1700
Data Index: 5854630 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8181. Min Act: -0.1700
Data Index: 924644 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8181. Min Act: -0.1700
Data Index: 5617077 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8181. Min Act: -0.1700
Data Index: 1798599 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.7869. Min Act: -0.1700
Data Index: 6123435 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.8181. Min Act: -0.1700
Data Index: 5846011 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1306. Min Range: -6.1306
Max Act: 5.7869. Min Act: -0.1700
Data Index: 2709316 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19