Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4436 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.4456. Min Act: -0.1700
Data Index: 4186580 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.3831. Min Act: -0.1700
Data Index: 2440618 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.3206. Min Act: -0.1700
Data Index: 339620 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.3206. Min Act: -0.1700
Data Index: 7224762 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.2581. Min Act: -0.1700
Data Index: 3616369 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.1331. Min Act: -0.1700
Data Index: 2686247 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.1331. Min Act: -0.1700
Data Index: 2237521 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.0706. Min Act: -0.1700
Data Index: 5126035 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.0706. Min Act: -0.1700
Data Index: 8155838 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.1331. Min Act: -0.1700
Data Index: 3622999 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.0081. Min Act: -0.1700
Data Index: 5566906 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.0081. Min Act: -0.1700
Data Index: 2659409 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.0081. Min Act: -0.1700
Data Index: 4986591 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.0081. Min Act: -0.1700
Data Index: 7063320 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4456. Min Range: -9.4456
Max Act: 9.0081. Min Act: -0.1700
Data Index: 3399115 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4456. Min Range: -9.4456
Max Act: 8.8831. Min Act: -0.1700
Data Index: 1405240 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4456. Min Range: -9.4456
Max Act: 8.9456. Min Act: -0.1700
Data Index: 2417470 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4456. Min Range: -9.4456
Max Act: 8.9456. Min Act: -0.1700
Data Index: 6082930 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4456. Min Range: -9.4456
Max Act: 8.9456. Min Act: -0.1700
Data Index: 3382481 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4456. Min Range: -9.4456
Max Act: 8.8831. Min Act: -0.1700
Data Index: 4534723 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19