Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5266 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2151. Min Range: -7.2151
Max Act: 7.2151. Min Act: -0.1700
Data Index: 4055754 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2151. Min Range: -7.2151
Max Act: 7.1839. Min Act: -0.1700
Data Index: 4261613 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2151. Min Range: -7.2151
Max Act: 7.1214. Min Act: -0.1700
Data Index: 5656240 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2151. Min Range: -7.2151
Max Act: 7.1214. Min Act: -0.1700
Data Index: 1170795 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.9964. Min Act: -0.1700
Data Index: 7280312 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.9651. Min Act: -0.1700
Data Index: 3477171 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.9651. Min Act: -0.1700
Data Index: 1998974 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.9026. Min Act: -0.1700
Data Index: 8513838 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.9026. Min Act: -0.1700
Data Index: 8161882 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.9026. Min Act: -0.1700
Data Index: 4513796 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.8401. Min Act: -0.1700
Data Index: 8538736 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.8401. Min Act: -0.1700
Data Index: 2472408 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.8401. Min Act: -0.1700
Data Index: 7065073 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.8089. Min Act: -0.1700
Data Index: 92858 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.8089. Min Act: -0.1700
Data Index: 4282266 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.8089. Min Act: -0.1700
Data Index: 1632523 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.8089. Min Act: -0.1700
Data Index: 2792271 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.8401. Min Act: -0.1700
Data Index: 1909697 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.7776. Min Act: -0.1700
Data Index: 8135875 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2151. Min Range: -7.2151
Max Act: 6.8089. Min Act: -0.1700
Data Index: 4847369 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19