Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3905 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2819. Min Range: -5.2819
Max Act: 5.2819. Min Act: -0.1700
Data Index: 8013363 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.9381. Min Act: -0.1700
Data Index: 5473603 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7819. Min Act: -0.1700
Data Index: 1152500 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7819. Min Act: -0.1700
Data Index: 4537240 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7506. Min Act: -0.1700
Data Index: 930426 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7819. Min Act: -0.1700
Data Index: 3737616 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7506. Min Act: -0.1700
Data Index: 2945365 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7506. Min Act: -0.1700
Data Index: 2800189 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7506. Min Act: -0.1700
Data Index: 3744343 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7506. Min Act: -0.1700
Data Index: 5746212 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6569. Min Act: -0.1700
Data Index: 6688056 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6569. Min Act: -0.1700
Data Index: 6971498 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6569. Min Act: -0.1700
Data Index: 5871823 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6256. Min Act: -0.1700
Data Index: 2691372 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6256. Min Act: -0.1700
Data Index: 7982481 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.5944. Min Act: -0.1700
Data Index: 2336137 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6256. Min Act: -0.1700
Data Index: 3196179 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6256. Min Act: -0.1700
Data Index: 7617806 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.5944. Min Act: -0.1700
Data Index: 6195207 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.5944. Min Act: -0.1700
Data Index: 3905407 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19