Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.6216. Min Act: -0.1700
Data Index: 199863 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.5903. Min Act: -0.1700
Data Index: 3624337 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.4653. Min Act: -0.1700
Data Index: 2345000 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.4341. Min Act: -0.1700
Data Index: 894292 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.4341. Min Act: -0.1700
Data Index: 3909843 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.4028. Min Act: -0.1700
Data Index: 4841643 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.3716. Min Act: -0.1700
Data Index: 8610036 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.3716. Min Act: -0.1700
Data Index: 2374586 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.3091. Min Act: -0.1700
Data Index: 2817070 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.3403. Min Act: -0.1700
Data Index: 7704192 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.2778. Min Act: -0.1700
Data Index: 2090758 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.3091. Min Act: -0.1700
Data Index: 796306 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.2778. Min Act: -0.1700
Data Index: 4164394 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.3091. Min Act: -0.1700
Data Index: 2920880 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.2466. Min Act: -0.1700
Data Index: 5006391 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.2466. Min Act: -0.1700
Data Index: 3180457 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.2153. Min Act: -0.1700
Data Index: 8335455 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.2153. Min Act: -0.1700
Data Index: 6629926 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.2153. Min Act: -0.1700
Data Index: 8364996 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6216. Min Range: -4.6216
Max Act: 4.2153. Min Act: -0.1700
Data Index: 6655483 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19