Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0310. Min Range: -5.0310
Max Act: 5.0310. Min Act: -0.1700
Data Index: 3804954 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9997. Min Act: -0.1700
Data Index: 32124 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9997. Min Act: -0.1700
Data Index: 1003151 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9997. Min Act: -0.1700
Data Index: 5169062 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9997. Min Act: -0.1700
Data Index: 1007994 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9997. Min Act: -0.1681
Data Index: 5749101 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9997. Min Act: -0.1700
Data Index: 444820 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9997. Min Act: -0.1700
Data Index: 1286672 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9997. Min Act: -0.1700
Data Index: 7948718 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9997. Min Act: -0.1700
Data Index: 1141432 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9685. Min Act: -0.1700
Data Index: 3121243 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9685. Min Act: -0.1700
Data Index: 2169564 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9372. Min Act: -0.1700
Data Index: 7765783 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9060. Min Act: -0.1700
Data Index: 2770443 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9060. Min Act: -0.1700
Data Index: 1051781 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.9060. Min Act: -0.1700
Data Index: 3439033 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.8747. Min Act: -0.1700
Data Index: 5181238 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.8747. Min Act: -0.1700
Data Index: 2559862 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.8747. Min Act: -0.1700
Data Index: 2183632 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0310. Min Range: -5.0310
Max Act: 4.8747. Min Act: -0.1700
Data Index: 138259 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19